© 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-16K
    7. 2545
    Prev
    Next
    INDEX
    Explanations

    tokens starting with t

    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_16k_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
    ни
    1.15
    ка
    0.80
    та
    0.79
    ی
    0.76
    ุ
    0.74
    are
    0.71
    <0x0D>
    0.69
    ्रा
    0.69
    ри
    0.67
    ्ड
    0.66
    POSITIVE LOGITS
    T
    0.83
    b
    0.76
    0.73
    어
    0.73
    <
    0.70
     tots
    0.67
    ব্র
    0.66
    它
    0.64
    Sch
    0.64
    C
    0.64
    Activations Density 1.036%

    No Known Activations