© 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. 114958
    Prev
    Next
    INDEX
    Explanations

    tools needed, ! Every, qualities of

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

    categories and descriptions

    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
     गलवान
    0.50
     kabel
    0.46
     orden
    0.46
     韩
    0.45
     بشأن
    0.44
     quelque
    0.43
     ongles
    0.43
    𝔀
    0.42
     kontinu
    0.42
     habil
    0.42
    POSITIVE LOGITS
     Ultimately
    0.46
    strtotime
    0.45
    atmosphere
    0.44
    sigmaf
    0.44
     pharmac
    0.43
     Gourmet
    0.43
    trip
    0.43
    perspective
    0.42
    param
    0.41
    rnd
    0.41
    Activations Density 0.000%

    No Known Activations