© 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-262K
    7. 79694
    Prev
    Next
    INDEX
    Explanations

    media rooms

    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_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
    А
    0.58
    Опера
    0.57
    Пет
    0.52
    Са
    0.50
    Вер
    0.50
    Тех
    0.50
    被称为
    0.48
    ла
    0.48
    cę
    0.48
    чам
    0.47
    POSITIVE LOGITS
     snake
    0.49
    ๐
    0.46
    al
    0.46
     ”
    0.46
    istency
    0.46
    er
    0.46
     morality
    0.45
    alte
    0.45
    })_{
    0.45
     floor
    0.44
    Activations Density 0.000%

    No Known Activations