© 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. 65307
    Prev
    Next
    INDEX
    Explanations

    energetic, grappling, rudimentary

    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
    ،
    0.57
    、
    0.47
     impeller
    0.46
     mandrel
    0.45
     teammate
    0.43
    ，
    0.43
     mater
    0.42
    、「
    0.42
     ovary
    0.42
    pOt
    0.42
    POSITIVE LOGITS
    to
    0.44
     Motions
    0.38
    See
    0.38
    use
    0.37
    </div>
    0.37
     Repe
    0.37
    Repe
    0.37
    in
    0.37
    昼
    0.37
    見る
    0.36
    Activations Density 0.000%

    No Known Activations