© 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. 79042
    Prev
    Next
    INDEX
    Explanations

    listing roles or components

    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
    ياه
    0.47
    ultz
    0.44
    Vectors
    0.43
    examtype
    0.42
    lső
    0.42
    परीक्षा
    0.41
     காண
    0.41
    멈
    0.41
    뚫
    0.41
     sonidos
    0.40
    POSITIVE LOGITS
     Caution
    0.48
     mucous
    0.47
     severity
    0.47
     Anda
    0.46
     Severity
    0.45
     Beneficial
    0.44
     Praia
    0.44
     I
    0.43
     SN
    0.43
     cleavage
    0.43
    Activations Density 0.002%

    No Known Activations