© 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. 190792
    Prev
    Next
    INDEX
    Explanations

    dreams, bites, victory

    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
    detect
    0.40
    罗
    0.38
     أب
    0.38
    AB
    0.37
    訨
    0.37
    似的
    0.36
     masch
    0.36
    तीय
    0.34
    lick
    0.34
     Abr
    0.34
    POSITIVE LOGITS
    рын
    0.42
    ഡ്
    0.41
     ресто
    0.40
     চীনে
    0.40
    ީ
    0.39
     corrientes
    0.39
    ከሰ
    0.38
     гран
    0.38
     plato
    0.38
     अमिताभ
    0.37
    Activations Density 0.003%

    No Known Activations