© 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. 174136
    Prev
    Next
    INDEX
    Explanations

    rules and agreements

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

    language, technical terms, diversity

    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
    或
    0.47
     received
    0.43
     was
    0.42
     Fé
    0.42
     When
    0.41
     Unable
    0.41
    ↵
    0.40
     или
    0.40
     indicate
    0.40
     atau
    0.39
    POSITIVE LOGITS
    recognizable
    0.47
    eslint
    0.47
    orrag
    0.46
     بڑھ
    0.45
    ophagy
    0.45
     basaltes
    0.45
     reforma
    0.44
    龈
    0.44
     derivados
    0.44
    塑造
    0.44
    Activations Density 0.001%

    No Known Activations