© 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. 133295
    Prev
    Next
    INDEX
    Explanations

    academic, technical, or professional contexts

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

    technical and conceptual descriptions

    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
    munition
    0.47
    usted
    0.46
    Gru
    0.46
     start
    0.45
    arsen
    0.44
    Zug
    0.44
    ç
    0.44
    start
    0.44
    cycle
    0.43
     j
    0.43
    POSITIVE LOGITS
     Doctorate
    0.61
     colleague
    0.49
    同学
    0.48
     devenue
    0.48
     WebElement
    0.47
     chargée
    0.47
     computeEncoder
    0.46
     dédiée
    0.46
     suivie
    0.46
     Robotics
    0.45
    Activations Density 0.000%

    No Known Activations