© 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. 10-GEMMASCOPE-RES-131K
    7. 66953
    Prev
    Next
    INDEX
    Explanations

    classified ads or sales pitches

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

    The neuron fires on numeric tokens (digits, numbers, and number‐like sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </b>
    -1.52
     (
    -1.45
     we
    -1.42
     To
    -1.36
    是怎么回事
    -1.34
     see
    -1.34
     For
    -1.32
     P
    -1.31
     —
    -1.29
     get
    -1.28
    POSITIVE LOGITS
    立
    1.70
    來
    1.58
     ビキニ
    1.51
     auffi
    1.44
    <bos>
    1.43
    
    1.38
     菇
    1.34
     atof
    1.32
    桖
    1.32
     ſou
    1.31
    Activations Density 0.312%

    No Known Activations