© 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. 135576
    Prev
    Next
    INDEX
    Explanations

    many, all, do, TOC, clouds, up, SNAP, sure, sudden

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

    technical and foreign terms

    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
    движи
    0.49
    คาเดมี
    0.47
    Kya
    0.47
    ur
    0.45
     স্টোন
    0.45
    zak
    0.44
     ಆನಿ
    0.44
    ল
    0.43
    labor
    0.43
    eat
    0.42
    POSITIVE LOGITS
     congel
    0.55
     elegantes
    0.50
     elegante
    0.49
     எரி
    0.49
    ط
    0.48
     Str
    0.47
     Circular
    0.46
    க்கு
    0.46
     nuevo
    0.46
     hielo
    0.46
    Activations Density 0.000%

    No Known Activations