© 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
    5. 16-GEMMASCOPE-2-RES-16K
    7. 15226
    Prev
    Next
    INDEX
    Explanations

    loved most, working on, want to

    np_acts-logits-general · gemini-2.5-flash-lite

    passions, seat, awaiting, thinks, reference, surprise

    np_acts-logits-general · gemini-2.5-flash-lite

    mid-sentence narrative contexts

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مۇ
    0.59
     منسلک
    0.54
     আনুগত্য
    0.54
     날
    0.53
    }$;
    0.53
     kayna
    0.53
     하나
    0.52
     پیغمبر
    0.52
     Fäh
    0.50
    이자
    0.50
    POSITIVE LOGITS
    ス
    0.61
    後半
    0.58
     us
    0.57
     his
    0.56
     s
    0.55
     hacerse
    0.55
    รวจ
    0.54
     sees
    0.53
     picks
    0.53
    prove
    0.52
    Activations Density 1.157%

    No Known Activations