© 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. 178855
    Prev
    Next
    INDEX
    Explanations

    used, term, up, id, webs, developer, events, since, Harvest, comparison

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

    event details

    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
    Defer
    0.54
    Symbol
    0.51
    Suggestions
    0.51
    Switch
    0.50
    绞
    0.49
    Rek
    0.49
    Gun
    0.48
    Valor
    0.48
    switching
    0.47
    Conditional
    0.47
    POSITIVE LOGITS
     met
    0.54
     Performance
    0.47
     záb
    0.46
     ć
    0.45
     lì
    0.45
     ô
    0.44
     Connolly
    0.44
     $^{\
    0.44
     Performances
    0.44
     tre
    0.43
    Activations Density 0.000%

    No Known Activations