© 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. 193574
    Prev
    Next
    INDEX
    Explanations

    words followed by a descriptor

    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
    厙
    0.46
    writer
    0.41
     reformation
    0.40
     writer
    0.39
    Inclusive
    0.38
    iktar
    0.38
    䡇
    0.37
     femmin
    0.36
     generational
    0.36
    押
    0.36
    POSITIVE LOGITS
    enberg
    0.43
     nobles
    0.41
     Scully
    0.39
     elegans
    0.39
    eman
    0.38
     গন্ধ
    0.38
    setRoi
    0.38
    enje
    0.37
    elleen
    0.37
    encia
    0.36
    Activations Density 0.000%

    No Known Activations