© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40334
    Prev
    Next
    INDEX
    Explanations

    concentration gradient

    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
     yeni
    0.54
     يب
    0.52
    ث
    0.50
     moż
    0.49
     richesse
    0.49
     assembl
    0.48
     meilleures
    0.48
    ج
    0.47
     Meine
    0.46
    نا
    0.46
    POSITIVE LOGITS
     assists
    0.50
    header
    0.49
    slots
    0.49
    oward
    0.47
    onn
    0.46
    <(),
    0.46
    active
    0.45
    athlon
    0.44
    ontrol
    0.44
    assist
    0.44
    Activations Density 0.014%

    No Known Activations