© 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. 117353
    Prev
    Next
    INDEX
    Explanations

    speaks multiplescans.on the Graduateteam. speaks multiplescans.on the Graduateteam

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

    grills, version, preferences, speed, generally, exit

    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
    ność
    0.46
    hemm
    0.46
    けれど
    0.46
    ിലാ
    0.45
     cheerfully
    0.45
     permanec
    0.44
     hilfreich
    0.44
    쪼
    0.43
     Они
    0.42
     તેઓ
    0.42
    POSITIVE LOGITS
     cGraph
    0.47
    ेटिक
    0.46
     USSR
    0.46
    BST
    0.46
     कौशिक
    0.46
    бера
    0.45
    pSensor
    0.44
     oWord
    0.44
    </h2>
    0.44
    ATIVE
    0.44
    Activations Density 0.001%

    No Known Activations