© 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. 188646
    Prev
    Next
    INDEX
    Explanations

    cistern flush

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

    collateral, direction, conditional, why

    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
    ↵
    0.52
     &
    0.50
     displays
    0.49
     ESS
    0.46
     transactions
    0.43
     WATER
    0.43
     COST
    0.43
    などの
    0.42
     %
    0.42
    ags
    0.41
    POSITIVE LOGITS
    Decedent
    0.57
    OfDeath
    0.49
    બાદ
    0.46
    Khokhlov
    0.46
     pundits
    0.46
     الفرنسي
    0.46
     decedent
    0.46
     gême
    0.46
     Lukaku
    0.45
     மாநிலத்தில்
    0.45
    Activations Density 0.002%

    No Known Activations