© 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. 64647
    Prev
    Next
    INDEX
    Explanations

    script patterns

    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
     सप्लाई
    0.42
    疹
    0.41
    期的
    0.40
    <unused2125>
    0.40
     আগে
    0.40
     ম্যানে
    0.40
    விலான
    0.39
    IMA
    0.39
    KUR
    0.39
    志森
    0.39
    POSITIVE LOGITS
    а
    0.56
    a
    0.46
    다
    0.46
    с
    0.46
    нт
    0.46
    б
    0.45
    л
    0.45
     victimization
    0.45
     decorator
    0.44
    m
    0.44
    Activations Density 0.000%

    No Known Activations