© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212197
    Prev
    Next
    INDEX
    Explanations

    updated on date

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

    list of items

    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
    ING
    0.50
    (`/
    0.48
    自然的
    0.48
     Updating
    0.46
    NewCollection
    0.46
     জড়
    0.45
     交換
    0.45
    Filtering
    0.44
     これらの
    0.42
     シンプル
    0.42
    POSITIVE LOGITS
    癣
    0.51
     receta
    0.45
    <unused2155>
    0.45
     Padd
    0.44
     Lemb
    0.44
    astă
    0.43
    ூரில்
    0.43
    üste
    0.43
     citron
    0.42
    治疗
    0.42
    Activations Density 0.001%

    No Known Activations