© 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. 32740
    Prev
    Next
    INDEX
    Explanations

    percentages and units

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

    marketing slogans, dates, names

    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
     sam
    0.42
    emat
    0.42
    ämä
    0.39
    輌
    0.39
     .,
    0.39
    ave
    0.38
     iba
    0.38
     tive
    0.38
     vw
    0.37
    arbeitet
    0.37
    POSITIVE LOGITS
    诲
    0.44
    Roxy
    0.43
    ைகள்
    0.43
    法语
    0.41
    ʒ
    0.41
     سنو
    0.40
    🫡
    0.39
    蜢
    0.39
    ไซ
    0.39
    Savings
    0.39
    Activations Density 0.000%

    No Known Activations