© 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. 2896
    Prev
    Next
    INDEX
    Explanations

    percentages and fractions

    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
     it
    1.35
     a
    1.34
     an
    1.29
    し
    1.26
    ۔
    1.24
     you
    1.16
    는
    1.10
     ζωή
    1.09
    המ
    1.09
    手の
    1.08
    POSITIVE LOGITS
    us
    1.87
    ot
    1.40
    u
    1.30
    é
    1.29
    SE
    1.23
    IC
    1.20
    id
    1.16
    IS
    1.16
    t
    1.14
    is
    1.13
    Activations Density 0.086%

    No Known Activations