© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29510
    Prev
    Next
    INDEX
    Explanations

    dust motes dancing or disturbed

    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
     valuing
    0.45
    َى
    0.43
     とする
    0.43
    ǎi
    0.42
    ਿਲ
    0.42
    🤽
    0.41
    漕
    0.40
     карто
    0.40
     робити
    0.39
    верса
    0.39
    POSITIVE LOGITS
    protected
    0.43
    eram
    0.40
     Helps
    0.39
     Sal
    0.38
     duplicates
    0.38
    eas
    0.38
     you
    0.37
    e
    0.37
    Pre
    0.36
    org
    0.36
    Activations Density 0.003%

    No Known Activations