© 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. 135503
    Prev
    Next
    INDEX
    Explanations

    plains

    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
     AGR
    0.58
     Gazprom
    0.57
     RIA
    0.55
    铯
    0.55
     OPS
    0.55
     Trish
    0.54
     Punta
    0.54
     Potomac
    0.54
     CASA
    0.53
    咊
    0.52
    POSITIVE LOGITS
     weniger
    0.42
    ലൈ
    0.41
    r
    0.41
    check
    0.39
    食
    0.38
    do
    0.38
    Less
    0.38
    line
    0.38
    siehe
    0.38
    Weather
    0.38
    Activations Density 0.001%

    No Known Activations