© 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. 160647
    Prev
    Next
    INDEX
    Explanations

    honest-to-a-fault Jupiter

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

    this week or month

    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
     be
    0.49
     derivatives
    0.47
    ciences
    0.44
    衍生
    0.43
    /
    0.42
     zwischen
    0.42
     kjent
    0.42
     derivative
    0.41
     ein
    0.41
     mellom
    0.41
    POSITIVE LOGITS
     remedied
    0.50
     espont
    0.49
     spontaneity
    0.49
     ஆணைய
    0.48
     제출
    0.48
     هولندا
    0.48
    isać
    0.48
    ]，
    0.47
    ۷
    0.47
     legislator
    0.47
    Activations Density 0.000%

    No Known Activations