© 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. 143830
    Prev
    Next
    INDEX
    Explanations

    conceived duly

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

    recommendation letters

    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
     파
    0.47
     તેમના
    0.46
     상수
    0.46
     পরিপ্রে
    0.46
     이후
    0.46
    팸
    0.45
     애
    0.45
    場合は
    0.44
     방법을
    0.44
    पहरण
    0.44
    POSITIVE LOGITS
    тном
    0.44
    an
    0.42
    कांड
    0.41
    स्तक
    0.41
    burn
    0.41
    ியம்
    0.41
     Gewalt
    0.41
    a
    0.41
     choking
    0.40
     devotes
    0.40
    Activations Density 0.002%

    No Known Activations