© 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. 86115
    Prev
    Next
    INDEX
    Explanations

    noise

    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
    ’
    0.80
     redeeming
    0.64
     wok
    0.63
     économ
    0.61
     milky
    0.60
     supremely
    0.59
     wik
    0.57
     benefited
    0.57
    ոն
    0.57
     creamy
    0.57
    POSITIVE LOGITS
    ک
    0.67
    as
    0.62
    ce
    0.61
    да
    0.61
    ED
    0.61
    apture
    0.61
    izing
    0.59
    Biografia
    0.58
    stract
    0.57
    om
    0.57
    Activations Density 0.004%

    No Known Activations