© 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. 99757
    Prev
    Next
    INDEX
    Explanations

    low/high, hide, programming, bids

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

    course should, IQ tests, AI to

    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
    大量的
    0.47
    苏州
    0.43
    绯
    0.43
    ськ
    0.43
     clichés
    0.42
     všech
    0.42
    ோர்
    0.42
    Persistent
    0.42
    Checker
    0.42
    쫙
    0.42
    POSITIVE LOGITS
    vonne
    0.50
     whatnot
    0.46
    impi
    0.45
    ombang
    0.43
     תח
    0.43
    ambat
    0.43
    ದ್ದರಿಂದ
    0.42
    ancar
    0.42
     חלק
    0.42
     মোটামুটি
    0.41
    Activations Density 0.001%

    No Known Activations