© 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. 11766
    Prev
    Next
    INDEX
    Explanations

    AI platform designs

    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
    来
    0.44
    Min
    0.43
    b
    0.43
    ၊
    0.43
     رج
    0.41
     ചു
    0.41
    ia
    0.41
    進
    0.40
    ної
    0.40
    い
    0.40
    POSITIVE LOGITS
     stimulate
    0.41
     computations
    0.41
     पांड
    0.40
     mathematicians
    0.38
     computation
    0.38
    -]
    0.38
     spreadsheet
    0.38
     monuments
    0.37
     বোঝ
    0.37
     replicate
    0.37
    Activations Density 0.000%

    No Known Activations