© 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. 71647
    Prev
    Next
    INDEX
    Explanations

    foreign languages and scripts

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

    non-English characters

    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
    uale
    0.50
     reduced
    0.50
     йо
    0.49
     symbiotic
    0.48
     тощо
    0.48
     consciente
    0.47
     hambre
    0.47
     ތ
    0.47
     timber
    0.46
     apre
    0.46
    POSITIVE LOGITS
    Ked
    0.52
    Сі
    0.52
    Ж
    0.52
    Ки
    0.51
    kons
    0.51
    به
    0.50
    Portug
    0.50
    Esc
    0.50
    Пі
    0.49
    Ĕ
    0.49
    Activations Density 0.001%

    No Known Activations