© 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. 115972
    Prev
    Next
    INDEX
    Explanations

    specific nouns and common words

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

    cost, traffic, reasons, logic

    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
    鉗
    0.48
     જણાવ્યું
    0.41
    錨
    0.40
     placebo
    0.40
    當中
    0.40
     HBV
    0.39
    鉀
    0.39
    收聽
    0.39
    西
    0.39
    濵
    0.39
    POSITIVE LOGITS
    rk
    0.54
     ulic
    0.53
     derajat
    0.49
     birinci
    0.48
    ra
    0.48
     ark
    0.48
     grafik
    0.47
     peringkat
    0.47
    ön
    0.46
     przej
    0.46
    Activations Density 0.001%

    No Known Activations