© 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. 164274
    Prev
    Next
    INDEX
    Explanations

    as part of

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

    as part of

    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
    はなく
    0.52
    मिनी
    0.49
    其他
    0.48
    ╯
    0.48
    ൊന്നും
    0.46
    過ぎ
    0.45
    は
    0.45
    ሞ
    0.44
     கோயில்
    0.43
    ものは
    0.43
    POSITIVE LOGITS
     during
    0.47
     Biosciences
    0.43
     Ghanaians
    0.43
     |.
    0.43
     DURING
    0.43
    ̦
    0.42
     Announces
    0.42
    .|
    0.41
     Fundação
    0.41
    during
    0.41
    Activations Density 0.003%

    No Known Activations