© 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. 115844
    Prev
    Next
    INDEX
    Explanations

    injured servicemen, children, Abraham, trade secrets

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

    Check neighboring corners

    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
     tourism
    0.55
     esteemed
    0.55
     humiliation
    0.49
    ilience
    0.48
    ای
    0.48
     Tourism
    0.48
     disinformation
    0.47
    </u>
    0.47
     hypnosis
    0.47
     handicrafts
    0.46
    POSITIVE LOGITS
     />
    0.47
    。“
    0.47
    oč
    0.43
    ^{-
    0.43
    琰
    0.43
    $\$
    0.42
    옆
    0.42
    ેચ્છ
    0.42
    _.
    0.41
    elements
    0.41
    Activations Density 0.000%

    No Known Activations