© 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. 110277
    Prev
    Next
    INDEX
    Explanations

    luxury rental, marry Miss, reveal his

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

    costly

    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
     maneras
    0.52
     orgánica
    0.50
     терро
    0.50
    ᆻ
    0.49
    सदीय
    0.48
    ﾇ
    0.48
     พิจิก
    0.47
     ဘ
    0.47
     ámbitos
    0.47
     totalidad
    0.47
    POSITIVE LOGITS
    -
    0.46
    \
    0.45
    EMS
    0.45
    Age
    0.44
    '
    0.44
    2
    0.43
    ag
    0.43
    /
    0.43
     receiver
    0.42
    GPS
    0.42
    Activations Density 0.001%

    No Known Activations