© 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. 14338
    Prev
    Next
    INDEX
    Explanations

    even followed by a word

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

    introduces surprising details

    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
    ம்
    0.82
    า
    0.80
    k
    0.78
    のみ
    0.71
    માં
    0.69
    ই
    0.68
    क
    0.66
    い
    0.65
    é
    0.64
    $
    0.63
    POSITIVE LOGITS
    handedly
    0.70
     представить
    0.67
    ized
    0.60
    ği
    0.53
    眉头
    0.52
     ሳይ
    0.51
    .
    0.51
     несмотря
    0.50
    !}
    0.50
     dù
    0.50
    Activations Density 0.099%

    No Known Activations