© 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. 64961
    Prev
    Next
    INDEX
    Explanations

    especially in

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

    The neuron activates on numeric tokens (especially multi-digit numbers).

    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
     historischen
    -1.10
    oluble
    -1.05
    จึง
    -1.03
    cketed
    -0.99
     was
    -0.98
    <bos>
    -0.95
     ۱۲
    -0.93
     ибо
    -0.93
    ')}}
    -0.91
    Flas
    -0.90
    POSITIVE LOGITS
     where
    1.13
     we
    1.13
     sentarse
    1.01
    れました
    0.98
    佧
    0.97
     Água
    0.96
     basePath
    0.96
     PARSER
    0.95
    يئة
    0.94
     disregarding
    0.94
    Activations Density 0.034%

    No Known Activations