© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20713
    Prev
    Next
    INDEX
    Explanations

    programming constructs and biological structures

    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
    니까
    0.50
    Kalau
    0.44
    差距
    0.42
    績
    0.42
     alba
    0.41
    Overall
    0.41
    гана
    0.41
    гура
    0.39
    全球
    0.38
    人口
    0.38
    POSITIVE LOGITS
     literals
    0.47
     ciertos
    0.42
     Anwendung
    0.42
    ിക്കേണ്ട
    0.42
     lien
    0.42
    ഠ
    0.41
     concerning
    0.41
     ஏனெனில்
    0.41
     específicas
    0.40
    碐
    0.40
    Activations Density 0.006%

    No Known Activations