© 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. 6409
    Prev
    Next
    INDEX
    Explanations

    amb, Hong, but, vol, these, a, hold, https, fake, for

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

    lists of items or questions

    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
    枌
    0.29
     مذہ
    0.25
    <unused64>
    0.25
    াইব
    0.25
    <unused5>
    0.24
     działalności
    0.24
     humains
    0.24
     жінок
    0.24
     জন্মের
    0.24
     människor
    0.24
    POSITIVE LOGITS
    i
    0.31
    T
    0.31
    k
    0.29
    a
    0.29
    ↵↵
    0.28
    ay
    0.27
    L
    0.27
    G
    0.27
    ↵
    0.27
    re
    0.26
    Activations Density 0.012%

    No Known Activations