© 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. 52816
    Prev
    Next
    INDEX
    Explanations

    or others (languages)

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

    accountability, received, versions

    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
    yrs
    0.44
    punkt
    0.43
    mine
    0.42
    druck
    0.42
    formats
    0.41
     perme
    0.40
     '
    0.39
    paste
    0.39
    visited
    0.39
     complimented
    0.39
    POSITIVE LOGITS
     또는
    0.59
     அல்லது
    0.57
     febrero
    0.55
     или
    0.54
    或
    0.53
     or
    0.52
     లేదా
    0.52
     または
    0.51
     ப்
    0.50
     ஏனெனில்
    0.50
    Activations Density 0.000%

    No Known Activations