© 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. 32450
    Prev
    Next
    INDEX
    Explanations

    Then applicable detective always CONTACT photographs Panel

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

    adjusting, trends, beyond

    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
    v
    0.60
     that
    0.52
     at
    0.46
    r
    0.46
    ellers
    0.46
     shouts
    0.46
    nare
    0.45
     abortions
    0.45
    l
    0.44
     newcomers
    0.44
    POSITIVE LOGITS
    젯
    0.59
    сед
    0.56
    یب
    0.55
    具合
    0.55
    хе
    0.55
     BuildableName
    0.54
    的气
    0.54
    мо
    0.53
    க்கழக
    0.53
     xếp
    0.53
    Activations Density 0.000%

    No Known Activations