© 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. 227514
    Prev
    Next
    INDEX
    Explanations

    located at

    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
    convergence
    0.54
    ᱖
    0.52
    ரிக்க
    0.49
     calves
    0.49
    identification
    0.47
    detection
    0.47
     identific
    0.47
     výkon
    0.47
     vá
    0.46
    liv
    0.46
    POSITIVE LOGITS
    Let
    0.54
    <h2>
    0.50
     grpc
    0.44
    Ag
    0.44
    <blockquote>
    0.43
    Oy
    0.43
    湟
    0.42
    พา
    0.42
    平成
    0.42
     disequ
    0.42
    Activations Density 0.003%

    No Known Activations