© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104490
    Prev
    Next
    INDEX
    Explanations

    U.S.P.Q. or P

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -1.67
     then
    -1.59
     knows
    -1.55
     by
    -1.54
     it
    -1.49
     dacă
    -1.46
    It
    -1.43
     fă
    -1.43
     çünkü
    -1.42
    他說
    -1.42
    POSITIVE LOGITS
    ieniem
    1.77
    吅
    1.64
    流畅
    1.53
     också
    1.50
    outWeight
    1.48
    ⸒
    1.47
    msub
    1.47
    kuwa
    1.46
     februar
    1.45
     {?}
    1.45
    Activations Density 0.001%

    No Known Activations