© 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. 21649
    Prev
    Next
    INDEX
    Explanations

    depends on conditions

    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
    льник
    0.45
     ликви
    0.43
    ÇÕES
    0.42
     उन्‍हें
    0.40
    приклад
    0.40
    সংস্কার
    0.39
     아직
    0.38
    敨
    0.38
     அவற்ற
    0.38
    циям
    0.38
    POSITIVE LOGITS
     of
    0.55
     during
    0.50
    随着
    0.46
     depends
    0.46
     During
    0.45
     Depends
    0.44
     periodically
    0.43
     periods
    0.43
    不仅仅
    0.43
    ตลอด
    0.42
    Activations Density 0.020%

    No Known Activations