© 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. 41-GEMMASCOPE-2-RES-262K
    7. 62848
    Prev
    Next
    INDEX
    Explanations

    drying agents

    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
    ճ
    0.45
     Substitution
    0.42
     practised
    0.41
    rarse
    0.37
    jwt
    0.37
    Jwt
    0.37
    팡
    0.37
    ោ
    0.36
     palpit
    0.36
    Ճ
    0.36
    POSITIVE LOGITS
     silica
    1.33
     Silica
    1.31
     adsorbent
    0.83
     desicc
    0.83
     silic
    0.80
     silice
    0.76
    干燥
    0.75
     drying
    0.72
     dess
    0.71
    乾燥
    0.71
    Activations Density 0.003%

    No Known Activations