© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50028
    Prev
    Next
    INDEX
    Explanations

    C# code constructs

    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
     into
    0.41
     components
    0.39
     in
    0.39
     XMFLOAT
    0.39
     lateral
    0.39
     blackboard
    0.38
     browned
    0.38
     i
    0.38
     copies
    0.38
     calories
    0.38
    POSITIVE LOGITS
    ӣ
    0.46
     सामग्रियों
    0.44
     moest
    0.43
    en
    0.42
    az
    0.42
     खड़ा
    0.42
    osław
    0.41
    ؛
    0.41
    ли
    0.41
     لكن
    0.41
    Activations Density 0.025%

    No Known Activations