© 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. 121319
    Prev
    Next
    INDEX
    Explanations

    campus

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

    AI-powered vision diagnostics

    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
     rendu
    0.52
     って
    0.49
     সুতরাং
    0.47
    ビ
    0.47
    々は
    0.47
     sentença
    0.45
     として
    0.45
     Wunsch
    0.45
     کنید
    0.45
     oiseaux
    0.45
    POSITIVE LOGITS
    falfa
    0.47
    a
    0.45
    daki
    0.44
    anque
    0.44
    ajara
    0.44
    ooky
    0.41
    chließlich
    0.41
    illian
    0.41
    amping
    0.41
     जाट
    0.41
    Activations Density 0.000%

    No Known Activations