© 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. 24688
    Prev
    Next
    INDEX
    Explanations

    requests and descriptions

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

    on purchases

    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
     случаев
    0.50
     шири
    0.49
     יכול
    0.48
     стара
    0.48
    트에
    0.48
     мебели
    0.47
     известно
    0.46
    '_{
    0.46
     креп
    0.46
    ках
    0.45
    POSITIVE LOGITS
    apor
    0.48
     August
    0.48
     ruler
    0.47
     But
    0.47
     Ground
    0.46
     ground
    0.43
     ra
    0.43
     retaining
    0.43
    por
    0.43
     both
    0.42
    Activations Density 0.001%

    No Known Activations