© 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. 72210
    Prev
    Next
    INDEX
    Explanations

    continue context

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

    empty lists

    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
    Prothorax
    0.58
    MinIntensity
    0.51
    𝗱
    0.50
    टाम
    0.49
    Nicht
    0.48
    Нет
    0.48
     señala
    0.46
    ()}>
    0.46
    Ƙ
    0.46
    าส
    0.45
    POSITIVE LOGITS
    အချိန်
    0.46
    不足
    0.45
     änd
    0.44
    ح
    0.44
     Sticker
    0.43
     Watertown
    0.43
     tiền
    0.43
     الحاس
    0.42
     المهم
    0.42
     exempel
    0.41
    Activations Density 0.000%

    No Known Activations