© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8885
    Prev
    Next
    INDEX
    Explanations

    positive attributes and states

    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_262k_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
    R
    0.51
    lf
    0.48
     הז
    0.43
    CT
    0.41
    N
    0.39
    K
    0.39
    Z
    0.39
    S
    0.39
    Y
    0.38
    J
    0.38
    POSITIVE LOGITS
     on
    0.50
    in
    0.49
    对待
    0.45
     while
    0.44
    ѝ
    0.42
     enough
    0.41
    eness
    0.41
     selama
    0.40
     kwenye
    0.40
     على
    0.40
    Activations Density 0.144%

    No Known Activations