© 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. 2196
    Prev
    Next
    INDEX
    Explanations

    most common type, convention, approach

    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
    UR
    0.54
    \
    0.53
    。
    0.53
    ם
    0.51
    レンズ
    0.50
    ネ
    0.49
    ヒ
    0.48
    ्रे
    0.48
    ِي
    0.48
    エ
    0.48
    POSITIVE LOGITS
    in
    1.07
    iest
    0.64
    igste
    0.64
    w
    0.62
     sweetest
    0.60
    at
    0.58
    ที่สุด
    0.58
     happiest
    0.56
     coolest
    0.55
     cutest
    0.54
    Activations Density 1.151%

    No Known Activations