© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84470
    Prev
    Next
    INDEX
    Explanations

    body parts and shapes

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of physical characteristics in animals, humans, or objects, particularly focusing on body shape and form.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects descriptive terms of an animal’s body conformation and physique (e.g. robust, chunky, cobby, muscular, massive, broad, well-muscled).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.61
    cinogenicity
    -1.44
     each
    -1.37
     by
    -1.33
     such
    -1.30
    JMenuBar
    -1.25
     explí
    -1.23
    ENCIÓN
    -1.20
    ViewChild
    -1.19
    sellors
    -1.18
    POSITIVE LOGITS
     overall
    1.21
     жили
    1.18
    sugges
    1.13
     ESPEC
    1.09
    ambassade
    1.08
     взгляд
    1.08
    lossene
    1.08
     arché
    1.07
    
    1.04
    calculated
    1.03
    Activations Density 0.023%

    No Known Activations