© 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. 90
    Prev
    Next
    INDEX
    Explanations

    explains or defines concepts

    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
     этом
    0.22
     этой
    0.19
     când
    0.19
     هذا
    0.18
     הם
    0.17
     這
    0.17
    ettes
    0.17
     देयर
    0.17
     этому
    0.17
     この
    0.16
    POSITIVE LOGITS
    A
    0.21
    HE
    0.21
    K
    0.20
    AB
    0.19
    Z
    0.19
    the
    0.18
    B
    0.18
    более
    0.17
     использование
    0.17
    PLS
    0.17
    Activations Density 1.357%

    No Known Activations