© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4003
    Prev
    Next
    INDEX
    Explanations

    sprite sheet

    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_16_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
    ing
    1.51
    us
    1.29
    ING
    1.25
    ara
    1.16
     (
    1.09
    िंग
    1.05
    ig
    1.03
    é
    1.02
    ian
    0.98
     of
    0.97
    POSITIVE LOGITS
    addSprite
    1.06
    。</
    1.01
    currentSprite
    1.00
    ジェクト
    0.96
     Sprite
    0.95
    ције
    0.93
     sprites
    0.93
     نہيں
    0.92
    ется
    0.92
    ции
    0.92
    Activations Density 0.015%

    No Known Activations