© 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. 31-GEMMASCOPE-2-RES-262K
    7. 77044
    Prev
    Next
    INDEX
    Explanations

    json format specification

    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_31_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
    အောင်
    0.54
     principales
    0.49
    YA
    0.46
    ⴽ
    0.46
    狠狠
    0.45
    ंगिक
    0.45
    semester
    0.43
    Экс
    0.43
     класс
    0.42
     calculi
    0.42
    POSITIVE LOGITS
    UILLER
    0.45
     de
    0.44
     gateway
    0.43
    oes
    0.43
    socketState
    0.43
    á
    0.42
     postaje
    0.41
    ການ
    0.41
    ap
    0.41
    one
    0.40
    Activations Density 0.000%

    No Known Activations