© 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. 34-GEMMASCOPE-RES-131K
    4. 33687
    Prev
    Next
    INDEX
    Explanations

    Former President titles

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

    This neuron fires on hardware specification tokens—numbers and alphanumeric model identifiers (e.g. “4,” “8,” “SATA,” “VM,” “AS ROCK”) used to denote technical specs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    жмите
    -0.79
    istiche
    -0.76
    isFunction
    -0.75
     betrifft
    -0.74
    
    -0.74
    RUB
    -0.74
    neri
    -0.73
    TextEdit
    -0.72
    ummings
    -0.72
     CSV
    -0.72
    POSITIVE LOGITS
    umpad
    0.73
    setCancelable
    0.69
     belongings
    0.67
    carro
    0.67
     отредактировал
    0.66
     value
    0.66
     bosom
    0.66
    済
    0.65
     northward
    0.64
    coop
    0.63
    Activations Density 0.030%

    No Known Activations