© 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. 51779
    Prev
    Next
    INDEX
    Explanations

    aword or phrase

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

    Alpaca

    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
    říklad
    0.44
    '
    0.43
     corporis
    0.42
    details
    0.42
    yez
    0.41
    ellem
    0.41
     birinci
    0.41
    heil
    0.40
    blick
    0.39
    细节
    0.39
    POSITIVE LOGITS
     ஆ
    0.56
     ใจ
    0.54
     स्टोक्स
    0.53
     冖
    0.53
     जानेवारी
    0.52
     หลาย
    0.49
    畠
    0.49
     शुक्रवार
    0.48
     ทุก
    0.48
     زمین
    0.48
    Activations Density 0.000%

    No Known Activations