© 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. 169926
    Prev
    Next
    INDEX
    Explanations

    let Brock take

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

    volume, higher, tools, potentially

    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
    uclease
    0.51
     bacterium
    0.50
    可以说
    0.47
     tenté
    0.47
    ές
    0.46
     pepp
    0.46
    ายน
    0.46
    凵
    0.45
     prefque
    0.45
     DNA
    0.45
    POSITIVE LOGITS
    Concurrent
    0.47
    Creation
    0.46
    Low
    0.45
    Parse
    0.44
    chop
    0.44
    Organ
    0.44
    Rejected
    0.44
    Paddle
    0.43
    Resolution
    0.42
    Expiration
    0.42
    Activations Density 0.001%

    No Known Activations