© 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. 134120
    Prev
    Next
    INDEX
    Explanations

    trail descriptions

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

    API, I, U, P, V, EC

    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
     массы
    0.57
    л
    0.57
     चिंत
    0.53
    चिंत
    0.52
    kiyor
    0.52
    кры
    0.52
    ijks
    0.50
    ч
    0.50
    ठमा
    0.49
    чины
    0.49
    POSITIVE LOGITS
     I
    0.52
    API
    0.49
     MPP
    0.48
     API
    0.46
     frown
    0.46
    I
    0.46
    ASC
    0.45
     عام
    0.44
     K
    0.43
     EMI
    0.43
    Activations Density 0.000%

    No Known Activations