© 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. 17450
    Prev
    Next
    INDEX
    Explanations

    to phrase structures

    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
     of
    0.73
    지
    0.67
    การ
    0.65
     
    0.63
    ब
    0.63
    ব
    0.61
    기
    0.61
     the
    0.60
    나
    0.60
    उ
    0.59
    POSITIVE LOGITS
     netted
    0.59
     також
    0.57
     reimb
    0.54
    ти
    0.53
    ка
    0.52
     internationales
    0.52
     فريبي
    0.51
    ០
    0.51
     پیسې
    0.50
     recharged
    0.50
    Activations Density 0.019%

    No Known Activations