© 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. 8082
    Prev
    Next
    INDEX
    Explanations

    as little as

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

    as, say, like

    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
    嬠
    0.33
    在了
    0.33
     wereld
    0.33
     আপনাদের
    0.31
     আগে
    0.31
    ிறார்
    0.31
    䂘
    0.30
     треба
    0.30
     আপনার
    0.30
    的時候
    0.30
    POSITIVE LOGITS
    '
    0.44
    of
    0.43
    -
    0.42
     as
    0.41
    1
    0.38
    a
    0.38
    i
    0.38
    ii
    0.37
    ’
    0.37
    ¬
    0.36
    Activations Density 0.394%

    No Known Activations