© 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. 80441
    Prev
    Next
    INDEX
    Explanations

    pronoun + punctuation

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

    effectiveness, models, researchers, share, problems

    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
    and
    0.64
    es
    0.59
    et
    0.55
    h
    0.53
    ல
    0.51
    for
    0.50
    f
    0.50
    k
    0.50
    rope
    0.49
    lar
    0.49
    POSITIVE LOGITS
     courte
    0.49
    جراء
    0.48
    দয়
    0.48
     paździer
    0.47
    writeToFile
    0.46
     yazd
    0.46
     적극
    0.46
    bindingFields
    0.46
    PAssignment
    0.46
     rédaction
    0.46
    Activations Density 0.000%

    No Known Activations