© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138333
    Prev
    Next
    INDEX
    Explanations

    partners or agents

    np_acts-logits-general · gemini-2.5-flash-lite

    stunts, of, goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    с
    0.69
     seine
    0.48
     ಪಡೆಯ
    0.47
    了他的
    0.46
     ஆதார
    0.45
    辖
    0.45
     decidedly
    0.44
     teeming
    0.44
    л
    0.43
    andan
    0.43
    POSITIVE LOGITS
     اولمپ
    0.46
    ﹁
    0.45
     anunciado
    0.43
     Turismo
    0.42
    čnog
    0.42
    פו
    0.41
     لمبے
    0.41
     být
    0.41
     Pharma
    0.41
    埤
    0.40
    Activations Density 0.000%

    No Known Activations