© 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. 41-GEMMASCOPE-2-RES-262K
    7. 6613
    Prev
    Next
    INDEX
    Explanations

    support

    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_all/layer_41_width_262k_l0_big
    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
     appreciably
    0.56
    রিষ্ঠ
    0.53
    ッサージ
    0.50
    }=(\
    0.49
     precisión
    0.49
     способом
    0.48
    フォーマンス
    0.48
    }}$;
    0.47
    ्रम
    0.46
     permeability
    0.46
    POSITIVE LOGITS
     Support
    0.99
     support
    0.88
    Support
    0.86
     suport
    0.75
    support
    0.71
     सपोर्ट
    0.70
    i
    0.66
    支持
    0.63
     Unterstützung
    0.63
     supporto
    0.63
    Activations Density 0.003%

    No Known Activations