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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208750
    Prev
    Next
    INDEX
    Explanations

    ranging from

    np_acts-logits-general · gemini-2.5-flash-lite

    Roman numeral section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ರೋ
    0.49
     주로
    0.46
     пункт
    0.45
    acked
    0.45
    addington
    0.44
     बढ़ाने
    0.43
     setback
    0.43
    가
    0.43
    Conditional
    0.42
     ಮಾ
    0.42
    POSITIVE LOGITS
    جي
    0.48
     unavoid
    0.47
    Ύ
    0.46
     división
    0.45
     líder
    0.43
     Codex
    0.43
    溟
    0.43
     Trit
    0.42
     déploy
    0.42
    طي
    0.42
    Activations Density 0.000%

    No Known Activations