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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25633
    Prev
    Next
    INDEX
    Explanations

    true/false answers

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

    The neuron fires on boolean literals, i.e. the tokens “true” and “false.”

    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
     from
    -1.19
     ebenfalls
    -1.14
     также
    -0.99
     również
    -0.94
     тоже
    -0.94
     також
    -0.92
     also
    -0.90
     još
    -0.89
     even
    -0.88
    ّم
    -0.87
    POSITIVE LOGITS
    쿠
    0.90
    sinki
    0.84
     yi
    0.80
    getX
    0.78
    ABET
    0.77
    äls
    0.76
     γ
    0.76
     ولي
    0.76
     Thoreau
    0.76
    tronlink
    0.75
    Activations Density 0.009%

    No Known Activations