© 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. 164074
    Prev
    Next
    INDEX
    Explanations

    dropping, continents, Pictures, regulating, into, floors, simply, graphic, proof, really

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

    # Ignore errors

    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
    PM
    0.59
    pur
    0.54
    po
    0.51
    m
    0.51
    bed
    0.50
    Only
    0.50
    dock
    0.48
    loud
    0.48
    hour
    0.48
     ຊ
    0.47
    POSITIVE LOGITS
    형
    0.52
    ْنَ
    0.50
     expectancy
    0.49
    ன்
    0.48
    skcipher
    0.48
    }^{*}=
    0.47
     Старки
    0.46
     zařízení
    0.46
    ம்தா
    0.46
     élections
    0.46
    Activations Density 0.000%

    No Known Activations