© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163679
    Prev
    Next
    INDEX
    Explanations

    contract, fan, actually, beer, least, Style, brush, generic, left, British

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

    conversational bot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ঘাঁটি
    0.47
     [])
    0.45
    ilingual
    0.43
    ynomial
    0.43
    ibouti
    0.42
     இப்போது
    0.41
     உண்மைய
    0.41
     ءَ
    0.41
     for
    0.40
    GES
    0.40
    POSITIVE LOGITS
     Cro
    0.41
    ;
    0.41
     কৌশল
    0.40
     Pioneers
    0.40
     Costume
    0.40
     Andi
    0.39
    育成
    0.39
     Latham
    0.38
     Grow
    0.38
    cropping
    0.38
    Activations Density 0.000%

    No Known Activations