© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47443
    Prev
    Next
    INDEX
    Explanations

    discussion topics and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ف
    0.56
    >(
    0.48
     XX
    0.47
    >\
    0.46
     (
    0.46
    Ges
    0.46
    >,
    0.46
     Attic
    0.45
     Xs
    0.45
     =
    0.45
    POSITIVE LOGITS
     догово
    0.43
     dawned
    0.42
    gradation
    0.41
    न्वयन
    0.41
     ejecución
    0.41
     discernible
    0.41
    급
    0.41
    icherung
    0.40
     contoured
    0.40
     configuración
    0.40
    Activations Density 0.000%

    No Known Activations