© 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. 60433
    Prev
    Next
    INDEX
    Explanations

    perfect and high quality

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

    descriptive words

    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
    ୍କ
    0.52
    Ꮸ
    0.49
    𝓟
    0.47
     ছিলেন
    0.46
    kę
    0.45
    らしく
    0.45
    全長
    0.44
     était
    0.44
    ছনে
    0.43
    coon
    0.42
    POSITIVE LOGITS
    ־
    0.54
     నో
    0.47
     نیز
    0.45
    -
    0.44
    ث
    0.43
     malign
    0.43
    岂
    0.42
     proteine
    0.41
     darum
    0.41
     احتجاج
    0.41
    Activations Density 0.000%

    No Known Activations