© 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-262K
    7. 41082
    Prev
    Next
    INDEX
    Explanations

    loading environment variables

    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_262k_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
     dehydration
    0.47
     clapping
    0.43
     dehyd
    0.42
    圤
    0.41
     tense
    0.41
     minted
    0.41
     lyophil
    0.41
     depolarization
    0.40
     galt
    0.40
     logra
    0.40
    POSITIVE LOGITS
     поворо
    0.47
    ﹒
    0.47
    Turning
    0.45
    ெட்
    0.44
    library
    0.43
     Turning
    0.43
    ogeneous
    0.43
     материа
    0.43
    نیا
    0.42
    Affine
    0.42
    Activations Density 0.001%

    No Known Activations