© 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. 7820
    Prev
    Next
    INDEX
    Explanations

    explain code and concepts

    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
    alım
    0.38
    פי
    0.37
    Casual
    0.36
    츨
    0.36
    ంగ
    0.34
    स्वागत
    0.34
    форд
    0.34
    ת
    0.34
    ཥ
    0.34
    策划
    0.33
    POSITIVE LOGITS
     also
    0.36
     de
    0.36
     another
    0.35
     vitamins
    0.34
     or
    0.34
     nebo
    0.34
     be
    0.33
     other
    0.33
     the
    0.33
     minerals
    0.33
    Activations Density 0.284%

    No Known Activations