© 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. 13642
    Prev
    Next
    INDEX
    Explanations

    time of day markers

    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
    0
    1.19
    1
    1.04
    k
    0.94
    ;
    0.67
    kst
    0.66
    mal
    0.64
    ı
    0.63
    IS
    0.63
    ]
    0.63
    </h2>
    0.62
    POSITIVE LOGITS
    то
    0.96
    น
    0.95
    ن
    0.86
    ли
    0.85
    ра
    0.84
     кораб
    0.83
    ла
    0.80
     drained
    0.80
    ต
    0.80
    alq
    0.79
    Activations Density 0.012%

    No Known Activations