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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 84873
    Prev
    Next
    INDEX
    Explanations

    flags and heraldry

    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_40_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
     buddha
    0.43
     डीएस
    0.42
     workflows
    0.40
    inline
    0.39
    RJ
    0.39
    ໊
    0.38
    ínu
    0.38
     Chub
    0.38
    cosystem
    0.37
    ઊ
    0.37
    POSITIVE LOGITS
     herald
    1.23
     Herald
    1.09
    Herald
    0.95
    herald
    0.93
     symbolism
    0.68
     heralded
    0.65
     अलं
    0.62
     medieval
    0.60
     tincture
    0.59
     vex
    0.59
    Activations Density 0.020%

    No Known Activations