© 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. 2760
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    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
    ):
    0.51
    al
    0.49
    ),
    0.48
    8
    0.47
    )}
    0.47
    in
    0.44
     Mitochond
    0.42
     plupart
    0.42
    inator
    0.42
    )(
    0.42
    POSITIVE LOGITS
    ー
    0.55
     що
    0.54
    いい
    0.54
    کی
    0.52
    트
    0.52
    리
    0.52
    ・
    0.50
    ן
    0.48
    १
    0.47
    多く
    0.46
    Activations Density 0.110%

    No Known Activations