© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115943
    Prev
    Next
    INDEX
    Explanations

    photo captions and blog tags

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

    This neuron strongly responds to digits and numeric tokens as well as apostrophe-based contractions (like ’s, ’ve, ’ll) often found in metadata, dates, and informal text.

    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
     kuliner
    -0.80
    vidla
    -0.78
    æv
    -0.76
     agricultural
    -0.75
     muhimu
    -0.71
    equality
    -0.71
     tiada
    -0.71
    thinkable
    -0.70
     campione
    -0.69
    クルマ
    -0.69
    POSITIVE LOGITS
     beleza
    1.06
    Homepage
    0.94
    Predicted
    0.88
     ahead
    0.88
    ፈ
    0.86
     zien
    0.85
    ždy
    0.83
     อ
    0.82
     mít
    0.81
    Documented
    0.80
    Activations Density 0.013%

    No Known Activations