© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7431
    Prev
    Next
    INDEX
    Explanations

    "Here", "you", "personal", "knowledge"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.77
    들
    0.76
    ای
    0.76
    들과
    0.75
    Bạn
    0.75
    Marne
    0.74
    ман
    0.74
    𝓼
    0.73
    лич
    0.73
    valentine
    0.73
    POSITIVE LOGITS
     legales
    0.78
     eso
    0.74
     certos
    0.73
     factorial
    0.73
     apres
    0.73
     ihn
    0.73
     cambios
    0.70
     ruedas
    0.70
     esa
    0.70
     actuar
    0.69
    Activations Density 0.000%

    No Known Activations