© 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. 90077
    Prev
    Next
    INDEX
    Explanations

    limited, in, means, close, every, Don, your, without

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

    blood through organs

    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
    ному
    0.52
     ס
    0.49
    твер
    0.47
    ్రు
    0.47
     carbur
    0.46
    ľ
    0.46
    \
    0.45
    <sup>
    0.45
     '${
    0.45
     debris
    0.45
    POSITIVE LOGITS
     lacs
    0.51
    asking
    0.48
    chained
    0.47
    HashSet
    0.45
     नीला
    0.45
     ہاتھوں
    0.44
    setAuto
    0.44
    mandatory
    0.44
    casa
    0.43
     ਗਿਆ
    0.43
    Activations Density 0.001%

    No Known Activations