© 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. 16-GEMMASCOPE-2-RES-262K
    4. 41547
    Prev
    Next
    INDEX
    Explanations

    speaker notes

    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
    AG
    0.61
    um
    0.60
    ل
    0.60
    IL
    0.57
    lip
    0.57
    isex
    0.56
    eto
    0.55
    bys
    0.55
    ig
    0.54
    al
    0.53
    POSITIVE LOGITS
    ಞ
    0.50
     televisión
    0.50
     makeshift
    0.49
     mourn
    0.48
     tash
    0.48
     convierten
    0.47
     tvam
    0.47
     থেকে
    0.46
     ghostly
    0.46
     ކުރ
    0.46
    Activations Density 0.000%

    No Known Activations