© 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. 190602
    Prev
    Next
    INDEX
    Explanations

    disclosed herein

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

    descriptive qualities of places

    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
     ভরে
    0.58
    Seit
    0.57
    涝
    0.52
     Seit
    0.49
     దా
    0.48
     muttered
    0.47
    तेक
    0.46
    ૂર્ણ
    0.46
     майже
    0.46
    ાઇલ
    0.46
    POSITIVE LOGITS
    ك
    0.59
    ش
    0.54
    ש
    0.54
    ی
    0.54
    م
    0.52
    म
    0.47
    ii
    0.47
     expon
    0.47
    الم
    0.46
    肩膀
    0.45
    Activations Density 0.000%

    No Known Activations