© 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. 31328
    Prev
    Next
    INDEX
    Explanations

    rejection, today, capture, themselves, wide, command

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

    all entirety forthwith

    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
    めっちゃ
    0.66
     kiddos
    0.59
     fizemos
    0.59
     crazy
    0.58
     collab
    0.57
     mūsų
    0.56
    😭
    0.55
     naše
    0.55
     👋
    0.55
     наших
    0.54
    POSITIVE LOGITS
     sämt
    0.64
     foodstuffs
    0.64
     sowohl
    0.57
     esche
    0.55
    觎
    0.55
     insofar
    0.53
     visage
    0.52
    गौरतलब
    0.51
     zarówno
    0.51
     bolstered
    0.49
    Activations Density 0.240%

    No Known Activations