© 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. 56885
    Prev
    Next
    INDEX
    Explanations

    starting and continuing

    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
     hemodynamic
    0.44
     underestimated
    0.43
    ItemStack
    0.42
    ጡ
    0.42
    ROT
    0.41
    YW
    0.41
    pval
    0.41
    Ⓒ
    0.41
    धानिक
    0.40
     perpend
    0.40
    POSITIVE LOGITS
    ?
    0.54
    อ
    0.54
     tad
    0.48
     soạn
    0.47
     در
    0.47
     Using
    0.47
    یا
    0.45
     Journey
    0.45
     Reading
    0.45
     Nhà
    0.45
    Activations Density 0.027%

    No Known Activations