© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30414
    Prev
    Next
    INDEX
    Explanations

    small steps forward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    発
    0.47
    "));
    0.44
    適
    0.43
     En
    0.42
     in
    0.42
    ار
    0.41
    :
    0.40
    MCA
    0.40
    ;
    0.40
     Bedrooms
    0.39
    POSITIVE LOGITS
    紵
    0.48
     модель
    0.47
     différente
    0.46
     модели
    0.45
     groceries
    0.45
    苖
    0.45
     роботи
    0.45
     бесплат
    0.45
     modell
    0.44
     boundless
    0.44
    Activations Density 0.001%

    No Known Activations