© 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. 243671
    Prev
    Next
    INDEX
    Explanations

    Monarch social sharing icons

    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
    руются
    0.46
    ResponseMessage
    0.45
    문의
    0.45
    hitth
    0.44
    стойчи
    0.43
    Confidence
    0.43
     барои
    0.43
    ি
    0.43
    Đáp
    0.42
    ли
    0.42
    POSITIVE LOGITS
     coincided
    0.49
     shortcut
    0.45
     square
    0.44
     بلو
    0.44
     contemporary
    0.43
     tweaked
    0.43
     rectangular
    0.42
     ended
    0.42
    ಿತು
    0.42
     truncated
    0.42
    Activations Density 0.000%

    No Known Activations