© 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. 178870
    Prev
    Next
    INDEX
    Explanations

    story about, flights, RX, washers, size

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

    body parts and structures

    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
    ٤
    0.47
     importance
    0.45
     sleepers
    0.44
    ွား
    0.44
     опро
    0.43
    ٥
    0.42
    r
    0.42
     improb
    0.42
    of
    0.41
    ب
    0.41
    POSITIVE LOGITS
     прове
    0.47
     ase
    0.47
    urangi
    0.47
     ढांचे
    0.47
     बिना
    0.46
     कठ
    0.46
    NESS
    0.45
    िकता
    0.45
    </bbox>
    0.45
    िकन
    0.45
    Activations Density 0.001%

    No Known Activations