© 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. 124785
    Prev
    Next
    INDEX
    Explanations

    free, glad, ultimate

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

    vocal strengths

    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
    Homepage
    0.55
     इंजीनियर
    0.48
     ঢেউ
    0.48
    Engineer
    0.48
     Jó
    0.48
    Bj
    0.47
     ഗവേഷ
    0.47
    嫐
    0.47
    ম্মদ
    0.46
    ја
    0.46
    POSITIVE LOGITS
    ’
    0.62
     testifying
    0.53
    س
    0.48
     lock
    0.46
     tenants
    0.46
     wall
    0.45
    壁
    0.45
    '
    0.45
     faktisk
    0.44
    units
    0.44
    Activations Density 0.000%

    No Known Activations