© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14379
    Prev
    Next
    INDEX
    Explanations

    following requirements

    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_40_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
    ei
    0.45
     tuv
    0.45
     it
    0.45
     upbeat
    0.44
    UP
    0.40
    l
    0.40
     upright
    0.39
    える
    0.39
    しま
    0.39
     upward
    0.38
    POSITIVE LOGITS
    完毕
    0.53
    ٺ
    0.46
     하고
    0.43
    이지만
    0.42
    nå
    0.41
     하는
    0.41
    thal
    0.41
    니다
    0.40
    嗟
    0.40
     전에
    0.40
    Activations Density 0.023%

    No Known Activations