© 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. 124702
    Prev
    Next
    INDEX
    Explanations

    question phrase beginnings

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

    technical terms and affiliations

    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
    "]),
    0.52
     overcrow
    0.50
     pai
    0.45
    )
    0.45
     escolares
    0.44
    arov
    0.43
     orice
    0.43
     Acceleration
    0.43
    ܟ
    0.42
    ့်
    0.42
    POSITIVE LOGITS
    ến
    0.55
    зи
    0.54
     conexión
    0.49
    ằng
    0.47
    ми
    0.46
    ен
    0.46
    ха
    0.45
    对着
    0.45
    ез
    0.44
     квартиры
    0.44
    Activations Density 0.001%

    No Known Activations