© 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. 71788
    Prev
    Next
    INDEX
    Explanations

    Awards, publications, invitations, located, example

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

    describing specific subjects

    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
    打电话
    0.46
     इन
    0.46
     von
    0.45
     Cavalry
    0.45
     ፕሮ
    0.44
     listens
    0.44
    贪
    0.43
     Bork
    0.43
    ‬
    0.42
     [
    0.42
    POSITIVE LOGITS
    clide
    0.52
    િજા
    0.50
     composição
    0.50
    ("--------
    0.49
    لاک
    0.48
    лиги
    0.47
    চ্ছন্দ
    0.47
    로드
    0.45
    драв
    0.45
    PathComponent
    0.45
    Activations Density 0.000%

    No Known Activations