© 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. 58585
    Prev
    Next
    INDEX
    Explanations

    cook as, his examination, the things

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

    lists or instructions

    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
     couv
    0.51
     کولو
    0.49
     توسیع
    0.48
    :");
    0.48
    (/(
    0.46
     intermedia
    0.46
     ");
    0.45
     :");
    0.45
     جوړونکی
    0.44
     taxa
    0.44
    POSITIVE LOGITS
    ഇ
    0.48
     angrily
    0.47
    im
    0.47
    istica
    0.45
    αι
    0.44
    ிக
    0.44
    ab
    0.43
    <strong>
    0.43
     deepest
    0.43
    ex
    0.42
    Activations Density 0.000%

    No Known Activations