© 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. 84982
    Prev
    Next
    INDEX
    Explanations

    distribution and measurements

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

    website titles

    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
     hypertro
    0.45
     carcinomas
    0.44
     männ
    0.42
     quân
    0.41
     warme
    0.41
    प्पा
    0.41
     hypothalamus
    0.41
    氯
    0.40
     急
    0.40
     cô
    0.40
    POSITIVE LOGITS
     implementation
    0.45
    pportune
    0.45
    ual
    0.43
    Implementation
    0.43
    implementation
    0.42
     enforceable
    0.41
     needs
    0.41
     director
    0.41
     recipient
    0.40
     Director
    0.40
    Activations Density 0.000%

    No Known Activations