© 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. 122176
    Prev
    Next
    INDEX
    Explanations

    early documentary minutes

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

    depends on

    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
    聽
    0.50
    </h2>
    0.50
    К
    0.49
    с
    0.49
    प
    0.49
    َ
    0.49
    প
    0.49
     output
    0.49
     outbound
    0.48
     offshore
    0.48
    POSITIVE LOGITS
    IdleSync
    0.48
     []),
    0.48
    ধবার
    0.48
     ദുൽ
    0.48
     एक्ट्रेसेस
    0.47
    CurrentImageData
    0.47
    カーボン
    0.46
     socketList
    0.46
     insectes
    0.46
    GetComponents
    0.46
    Activations Density 0.002%

    No Known Activations