© 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. 79841
    Prev
    Next
    INDEX
    Explanations

    body size and strength

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

    descriptions of a person's physical size, particularly height and weight measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     it
    -1.86
     each
    -1.20
     this
    -1.18
     time
    -1.13
     or
    -1.07
    ּוֹ
    -1.07
     while
    -1.05
     оно
    -1.04
     first
    -1.01
    pagestyle
    -1.00
    POSITIVE LOGITS
     physical
    1.48
     his
    1.36
     physique
    1.34
     size
    1.33
     kado
    1.27
     height
    1.21
    ORGE
    1.21
     gese
    1.20
     upcoming
    1.19
     Size
    1.17
    Activations Density 0.019%

    No Known Activations