© 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. 168349
    Prev
    Next
    INDEX
    Explanations

    download driver

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

    list formatting and structure

    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
    '
    0.50
    }
    0.46
    Case
    0.46
    0
    0.46
    *
    0.45
    <code>
    0.44
    umber
    0.43
    "
    0.42
    inches
    0.42
    ن
    0.42
    POSITIVE LOGITS
    SXml
    0.53
    ResBuffer
    0.52
     жөн
    0.50
     mardi
    0.50
     گذشته
    0.49
     вчера
    0.49
     mercredi
    0.48
     березня
    0.47
    ೊಳ
    0.47
     maksud
    0.46
    Activations Density 0.001%

    No Known Activations