© 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. 73338
    Prev
    Next
    INDEX
    Explanations

    bears, faux, thanks

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

    release steam or tower

    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
    n
    0.50
    เร็ว
    0.47
     AcOEt
    0.46
     คร
    0.45
     էր
    0.45
    surfing
    0.45
    ใ
    0.45
    ד
    0.45
     SOME
    0.42
     மில்லியன்
    0.42
    POSITIVE LOGITS
     ejecución
    0.47
     Precinct
    0.47
     precinct
    0.47
     as
    0.46
    シルバー
    0.46
     demand
    0.44
     crane
    0.43
     مدينه
    0.43
     comport
    0.43
     incentiv
    0.42
    Activations Density 0.003%

    No Known Activations