© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1699
    Prev
    Next
    INDEX
    Explanations

    math and leaning actions

    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_40_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
    teki
    0.39
     দেড়
    0.39
     scorecard
    0.39
    Chick
    0.38
    ላት
    0.38
    тику
    0.38
    髖
    0.38
    寿司
    0.38
     sciatic
    0.38
    ёшь
    0.38
    POSITIVE LOGITS
     xmlns
    0.77
    xmlns
    0.73
    baseline
    0.50
    ><
    0.49
     Baseline
    0.49
     baseline
    0.44
    S
    0.44
     бази
    0.44
    version
    0.43
    真正
    0.41
    Activations Density 0.000%

    No Known Activations