© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45808
    Prev
    Next
    INDEX
    Explanations

    low entropy

    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
     جسم
    0.46
    osevelt
    0.44
     ooit
    0.42
    餸
    0.42
     कॉमर्स
    0.42
     Нача
    0.41
     sintomi
    0.41
     emozioni
    0.41
     изобре
    0.41
     발전
    0.41
    POSITIVE LOGITS
    メイク
    0.49
    ิบ
    0.47
    n
    0.47
     dresses
    0.46
    ्रेन
    0.45
     renou
    0.44
    ドレス
    0.44
    ิ
    0.44
    erad
    0.43
    ியுடன்
    0.43
    Activations Density 0.001%

    No Known Activations