© 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. 143075
    Prev
    Next
    INDEX
    Explanations

    monitor or

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

    Record, Document, Models

    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
     Rankin
    0.49
    áról
    0.48
     aus
    0.47
     Beatty
    0.46
    ísk
    0.45
    iss
    0.44
     Deane
    0.44
    á
    0.44
     tats
    0.44
     McMillan
    0.43
    POSITIVE LOGITS
     moc
    0.56
    サン
    0.55
    する
    0.54
    POC
    0.50
    取り
    0.49
    ゲン
    0.49
    BOX
    0.48
    न्छ
    0.48
    色の
    0.47
    産の
    0.47
    Activations Density 0.000%

    No Known Activations