© 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. 12140
    Prev
    Next
    INDEX
    Explanations

    steps numbered

    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
     whose
    -2.13
     during
    -2.11
     after
    -2.09
     sehr
    -1.89
     until
    -1.88
     using
    -1.85
     every
    -1.84
     just
    -1.84
     aimed
    -1.74
     a
    -1.73
    POSITIVE LOGITS
     wonderful
    1.66
     bascul
    1.63
     flamboyant
    1.63
     hefty
    1.63
    eight
    1.61
     blatant
    1.60
     relentless
    1.57
     {
    1.54
    disfraz
    1.52
     hig
    1.52
    Activations Density 0.008%

    No Known Activations