© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206299
    Prev
    Next
    INDEX
    Explanations

    cardinals and emerald

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

    long, healthy life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    antis
    0.54
     comprennent
    0.50
    signals
    0.49
    пуск
    0.48
    θ
    0.48
    蝼
    0.48
    dimensions
    0.46
    etik
    0.46
    definitions
    0.46
    aspect
    0.46
    POSITIVE LOGITS
     Neuen
    0.49
     cardinals
    0.46
     Emerald
    0.46
    忶
    0.46
     emerald
    0.46
    យ៉
    0.46
     വെള്ള
    0.45
     Arn
    0.45
     verd
    0.45
     Cardinals
    0.44
    Activations Density 0.000%

    No Known Activations