© 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. 2617
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
    د
    1.01
    ש
    0.88
    ב
    0.86
    ون
    0.81
    자
    0.81
    هم
    0.79
    ম
    0.78
    י
    0.77
    ก
    0.77
    تے
    0.76
    POSITIVE LOGITS
    is
    0.76
    on
    0.61
    ů
    0.56
     verein
    0.53
    Kunst
    0.53
    ci
    0.52
     erfolgte
    0.52
    0
    0.52
    for
    0.51
     decembrie
    0.51
    Activations Density 0.044%

    No Known Activations