© 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. 29831
    Prev
    Next
    INDEX
    Explanations

    service and error attributes

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

    schema.org, VSSO, RDF, JSON, TLS, ALB, FHI R, properties, fields

    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
    ◑
    0.48
    嶺
    0.48
    ೇಶ್
    0.46
     זי
    0.46
    壺
    0.45
     ジ
    0.44
     रुद्र
    0.44
    蕃
    0.44
     ይች
    0.44
     حسین
    0.44
    POSITIVE LOGITS
    omitempty
    0.61
     optional
    0.59
     specified
    0.58
     specifying
    0.56
    optional
    0.55
     Optional
    0.54
     defined
    0.50
     attributes
    0.49
     Kafka
    0.49
     underscored
    0.49
    Activations Density 0.002%

    No Known Activations