© 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. 40842
    Prev
    Next
    INDEX
    Explanations

    replacing items

    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
    ва
    0.71
     जिनसे
    0.64
    드가
    0.62
    ض
    0.61
    కుని
    0.61
    まります
    0.61
    ١
    0.61
     požad
    0.60
    venty
    0.59
     которыми
    0.59
    POSITIVE LOGITS
    the
    0.80
    s
    0.78
    in
    0.67
     waterproof
    0.64
    ím
    0.58
    r
    0.57
    7
    0.57
    ่า
    0.57
    íme
    0.56
     synchronize
    0.55
    Activations Density 0.002%

    No Known Activations