© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17815
    Prev
    Next
    INDEX
    Explanations

    Code constructs and commands

    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
     ہے۔
    0.43
     jų
    0.41
    ۔
    0.41
     ශ
    0.40
    ное
    0.39
     of
    0.37
    ่
    0.37
     +:+
    0.36
    ).)
    0.36
     ។
    0.35
    POSITIVE LOGITS
     I
    0.36
     considere
    0.34
    I
    0.33
     resurrect
    0.30
     Carthage
    0.29
    they
    0.28
    bomb
    0.28
     rectangles
    0.28
     átomos
    0.28
    gob
    0.28
    Activations Density 0.115%

    No Known Activations