© 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. 161340
    Prev
    Next
    INDEX
    Explanations

    Silurian property students

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

    sections starting with "The Problem"

    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
     පසු
    0.51
     rež
    0.48
     breakdowns
    0.48
     régime
    0.47
     ð
    0.46
     जहाज़
    0.46
     telefonu
    0.46
     János
    0.46
     território
    0.46
     ناو
    0.45
    POSITIVE LOGITS
    ема
    0.42
    o
    0.40
    assignmentItems
    0.40
    падает
    0.40
    ЕН
    0.39
     tộc
    0.39
    ూ
    0.39
    켄
    0.39
    rng
    0.38
    oq
    0.38
    Activations Density 0.000%

    No Known Activations