© 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. 203600
    Prev
    Next
    INDEX
    Explanations

    commercial level or card effects

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

    hiding complex implementation details

    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
     salió
    0.51
    турой
    0.47
    溸
    0.46
     verb
    0.46
     situado
    0.46
     werd
    0.45
    ק
    0.45
     producción
    0.45
     رفتار
    0.45
     教
    0.44
    POSITIVE LOGITS
     encompassing
    0.53
     albeit
    0.47
     awaiting
    0.44
    aggregated
    0.44
    margins
    0.44
    ঙ্কার
    0.44
     عوامی
    0.43
     अद्भ
    0.43
     attributable
    0.43
    workers
    0.42
    Activations Density 0.000%

    No Known Activations