© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126431
    Prev
    Next
    INDEX
    Explanations

    parents, relationships, cause

    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
     in
    0.58
     o
    0.51
     a
    0.48
     Decide
    0.47
     Xcode
    0.47
     финан
    0.47
     ir
    0.46
     doct
    0.46
     understatement
    0.46
     ri
    0.45
    POSITIVE LOGITS
    pitch
    0.47
    ಗಳಿವೆ
    0.44
     largura
    0.44
     রহমান
    0.41
     zegt
    0.41
    <unused75>
    0.41
    পথ
    0.41
    weile
    0.40
    ವೂ
    0.40
     yolu
    0.40
    Activations Density 0.000%

    No Known Activations