© 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. 137943
    Prev
    Next
    INDEX
    Explanations

    articles and pronouns followed by content

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

    explaining direction of research

    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
    פ
    0.45
    산업
    0.44
    ods
    0.42
    ina
    0.41
    in
    0.40
    s
    0.40
     কোথ
    0.39
     산업
    0.39
    ত
    0.39
    ua
    0.39
    POSITIVE LOGITS
     („
    0.44
     roofs
    0.42
     cephal
    0.42
    HairColor
    0.42
     मजेदार
    0.42
     houses
    0.41
     आहोत
    0.41
    BoolVar
    0.41
     booze
    0.41
     skyscrapers
    0.40
    Activations Density 0.000%

    No Known Activations