© 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. 15557
    Prev
    Next
    INDEX
    Explanations

    a or to followed by noun

    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
     بأن
    0.33
     أن
    0.32
     når
    0.32
     براي
    0.32
     २५
    0.32
    あります
    0.31
    ８
    0.31
     assumes
    0.30
    ༢
    0.30
    ｊ
    0.30
    POSITIVE LOGITS
    τικών
    0.27
    </h1>
    0.27
     Kids
    0.26
     Hotels
    0.25
     Hotel
    0.25
     Productions
    0.25
     Ext
    0.25
    GIT
    0.25
     Casino
    0.25
     sesuatu
    0.25
    Activations Density 0.086%

    No Known Activations