© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 52573
    Prev
    Next
    INDEX
    Explanations

    .edu domains

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

    multi-language code snippets

    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
    y
    0.68
    0
    0.68
    h
    0.66
    w
    0.64
    m
    0.63
    r
    0.62
    s
    0.61
    is
    0.61
    l
    0.57
    b
    0.57
    POSITIVE LOGITS
     ausreiche
    0.49
     ausreichend
    0.44
    屢
    0.43
     siente
    0.43
     しかし
    0.43
     algorit
    0.42
     රා
    0.42
     //-
    0.41
     //[
    0.41
     estábamos
    0.41
    Activations Density 0.006%

    No Known Activations