© 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. 41249
    Prev
    Next
    INDEX
    Explanations

    when compared

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

    argument tells / argument uses

    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
    у
    0.52
    ،
    0.45
    )$
    0.43
     elit
    0.43
    prima
    0.42
    ту
    0.42
     مؤرشف
    0.42
    끄
    0.41
    that
    0.41
     इतना
    0.41
    POSITIVE LOGITS
     landlab
    0.56
     kesalahan
    0.49
    วัสดี
    0.48
     metallurgical
    0.46
     tàu
    0.45
     trails
    0.44
     välja
    0.44
     reveló
    0.44
     moored
    0.44
     deer
    0.43
    Activations Density 0.000%

    No Known Activations