© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111593
    Prev
    Next
    INDEX
    Explanations

    resonance phenomena

    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
     scritta
    -2.08
     Infór
    -1.93
     to
    -1.92
    ౮
    -1.87
     utilizzata
    -1.85
     Würde
    -1.83
     Pastikan
    -1.80
     sagde
    -1.79
     褲
    -1.78
    行って
    -1.75
    POSITIVE LOGITS
    '
    1.88
    ↵
    1.87
    (
    1.84
    </b>
    1.76
    お好み
    1.68
    \
    1.64
     amitié
    1.56
     ostavi
    1.53
    })$,
    1.52
     další
    1.51
    Activations Density 0.016%

    No Known Activations