© 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. 59296
    Prev
    Next
    INDEX
    Explanations

    our website

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

    measuring grain, Early Industry, Session Lifetime

    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
     judíos
    0.56
     Tutto
    0.50
    लैंड
    0.50
     palabras
    0.49
     estil
    0.48
     ezzel
    0.48
     empez
    0.47
    司
    0.46
    licos
    0.45
    ارا
    0.45
    POSITIVE LOGITS
    <0x0D>
    0.51
    '
    0.51
     Reform
    0.45
    led
    0.45
     Normal
    0.44
     scheme
    0.44
    ments
    0.43
     formats
    0.43
     context
    0.43
     shell
    0.43
    Activations Density 0.000%

    No Known Activations