© 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. 160818
    Prev
    Next
    INDEX
    Explanations

    URL creation

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

    technical terms and lists

    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
    Berlin
    0.54
    ]");
    0.49
    бовать
    0.46
    ים
    0.46
     Джон
    0.45
     PackageManager
    0.45
    ándolo
    0.44
     バック
    0.44
    Relations
    0.44
    Allemagne
    0.44
    POSITIVE LOGITS
    n
    0.55
    립
    0.50
     typo
    0.49
     Sect
    0.47
    ن
    0.47
     haircut
    0.47
     vaid
    0.47
     तब्
    0.46
     greed
    0.46
     buggy
    0.46
    Activations Density 0.000%

    No Known Activations