© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2134
    Prev
    Next
    INDEX
    Explanations

    run or execute code

    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_16_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
    も
    0.74
    ও
    0.73
    ESSITY
    0.66
    も含
    0.66
    க்
    0.63
    ນີ້
    0.59
    ۰
    0.59
    ON
    0.59
    𝓗
    0.57
    Istituto
    0.57
    POSITIVE LOGITS
    िक
    0.77
    ə
    0.75
    is
    0.74
    ان
    0.69
    an
    0.68
    ين
    0.67
    ک
    0.66
    وم
    0.64
    ى
    0.63
    ik
    0.61
    Activations Density 0.544%

    No Known Activations