© 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. 80007
    Prev
    Next
    INDEX
    Explanations

    scientific reference proceedings

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

    Spanish and French words

    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
    Ꮡ
    0.57
    ابق
    0.50
     tiszt
    0.49
     isometry
    0.49
    诚信
    0.47
    幫
    0.46
     PDC
    0.46
     Gemeind
    0.46
    佸
    0.45
    づくり
    0.45
    POSITIVE LOGITS
    OMBRE
    0.52
    ANO
    0.49
    ombres
    0.49
     zeros
    0.48
    oola
    0.47
    galo
    0.47
    embro
    0.44
    cL
    0.44
    CUT
    0.44
    ORDER
    0.44
    Activations Density 0.000%

    No Known Activations