© 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. 155367
    Prev
    Next
    INDEX
    Explanations

    formats! next-generation weapon download links projects insulting issue

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

    system stability

    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
    водит
    0.55
    genetic
    0.49
    Genetic
    0.46
    га
    0.45
    ਿਲ
    0.45
    ोरा
    0.45
     ระ
    0.45
    ਸ
    0.45
    prav
    0.44
    direita
    0.44
    POSITIVE LOGITS
     innumerable
    0.48
    endo
    0.47
    %,
    0.47
     ഒരിക്ക
    0.45
    ([],
    0.45
     numerosos
    0.44
     uni
    0.44
    usions
    0.43
     unil
    0.43
     Sir
    0.42
    Activations Density 0.001%

    No Known Activations