© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    name followed by assignment

    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
    ت
    0.88
    д
    0.84
    ب
    0.82
    <0x80>
    0.75
    0
    0.70
    '
    0.68
    т
    0.68
    ್ಟ
    0.67
    ைட்
    0.66
    мб
    0.64
    POSITIVE LOGITS
     name
    0.77
    ור
    0.69
    ला
    0.67
     than
    0.65
     as
    0.65
     who
    0.63
     but
    0.63
     you
    0.62
    리
    0.60
    ገድ
    0.59
    Activations Density 0.215%

    No Known Activations