© 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. 16-GEMMASCOPE-2-RES-65K
    7. 1571
    Prev
    Next
    INDEX
    Explanations

    on behalf

    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
    Q
    1.55
    d
    1.48
    K
    1.41
    Z
    1.40
    O
    1.39
    in
    1.38
    M
    1.29
    J
    1.22
    B
    1.15
    W
    1.10
    POSITIVE LOGITS
     on
    1.92
     to
    1.52
    ку
    1.48
    on
    1.42
    리
    1.40
    ن
    1.39
     was
    1.38
    ก
    1.24
     that
    1.17
    ри
    1.17
    Activations Density 0.424%

    No Known Activations