© 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. 46488
    Prev
    Next
    INDEX
    Explanations

    lichen

    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
    荠
    0.58
     сня
    0.54
     υπο
    0.54
    利
    0.54
     profundidad
    0.53
    সি
    0.52
    িউ
    0.52
     brilh
    0.52
     اله
    0.51
     свойства
    0.51
    POSITIVE LOGITS
     to
    0.63
    !
    0.60
    ?
    0.60
    ERS
    0.55
     can
    0.55
     does
    0.55
    ED
    0.53
    cker
    0.52
     lorsqu
    0.50
    a
    0.50
    Activations Density 0.000%

    No Known Activations