© 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. 134334
    Prev
    Next
    INDEX
    Explanations

    available, shapes, problem, ways, who, research

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

    options, alternatives, or subsequent actions

    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
     BGPS
    0.52
     फाय
    0.49
     सुरक्षित
    0.49
     شدہ
    0.48
     छत
    0.47
     ಅಗತ್ಯ
    0.46
    azam
    0.45
    ”
    0.45
    ⟋
    0.44
     Airtel
    0.44
    POSITIVE LOGITS
     verwend
    0.46
    বিষয়
    0.46
    ן
    0.45
    <
    0.44
    ohan
    0.44
    м
    0.44
    ي
    0.44
    ais
    0.44
    শা
    0.43
    a
    0.43
    Activations Density 0.000%

    No Known Activations