© 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. 109127
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

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

    variables, equations, and numbers

    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
    ્વાસ
    0.41
    тре
    0.40
    성이
    0.39
    성에
    0.39
    쾌
    0.39
    тить
    0.38
    성과
    0.38
     політи
    0.38
    등급
    0.37
     childlike
    0.37
    POSITIVE LOGITS
     Dain
    0.47
     Kain
    0.43
     Singers
    0.43
     Ryu
    0.42
     Bae
    0.41
     Mot
    0.41
     Bxf
    0.41
    stdc
    0.40
     ベージュ
    0.40
    k
    0.40
    Activations Density 0.000%

    No Known Activations