© 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. 77066
    Prev
    Next
    INDEX
    Explanations

    ai and languages

    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
     BasicContainer
    0.44
     মসজি
    0.42
     উক
    0.40
    栤
    0.39
     င
    0.39
     Style
    0.38
     $($
    0.38
    ఏ
    0.38
     জমা
    0.38
    icago
    0.37
    POSITIVE LOGITS
    respons
    0.42
     trium
    0.40
    shader
    0.40
     murderous
    0.39
    ω
    0.39
     truce
    0.38
     northward
    0.38
    他的
    0.38
     he
    0.38
    the
    0.37
    Activations Density 0.000%

    No Known Activations