© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11748
    Prev
    Next
    INDEX
    Explanations

    model's structure or syntax

    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_65k_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
    )}}{\
    0.39
    über
    0.37
     meek
    0.36
     lebens
    0.36
    )}^{\
    0.35
    estim
    0.34
    כל
    0.34
    laden
    0.34
    르
    0.34
     את
    0.34
    POSITIVE LOGITS
    ’
    0.29
     analysis
    0.28
     Curve
    0.28
     xử
    0.27
     diarr
    0.26
     nhận
    0.26
     flavonoid
    0.26
     Directory
    0.26
     Guide
    0.26
     hướng
    0.26
    Activations Density 0.351%

    No Known Activations