© 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. 31807
    Prev
    Next
    INDEX
    Explanations

    sync across devices

    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
    i
    1.11
     was
    1.05
    in
    1.04
    ;
    0.91
    ي
    0.90
     in
    0.89
    iation
    0.84
    น
    0.80
    0.80
    e
    0.79
    POSITIVE LOGITS
    ای
    1.35
    Sync
    1.02
    리
    0.95
    SYNC
    0.91
    Synchronization
    0.89
    同步
    0.88
    Synchron
    0.88
    을
    0.86
    લ
    0.86
    ため
    0.86
    Activations Density 0.012%

    No Known Activations