© 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. 165790
    Prev
    Next
    INDEX
    Explanations

    state of New York

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

    questions, tests, or lists

    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
    На
    0.52
    嗘
    0.48
     *_
    0.46
     اجر
    0.46
     dzieci
    0.46
    Де
    0.45
     کئی
    0.45
     bambini
    0.45
     collation
    0.43
    ᠠ
    0.42
    POSITIVE LOGITS
    simmons
    0.54
    blockquote
    0.47
    emploi
    0.47
    柴
    0.47
    חד
    0.46
    ால
    0.46
    nikov
    0.46
    raham
    0.45
    rath
    0.45
    mene
    0.45
    Activations Density 0.001%

    No Known Activations