© 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. 129926
    Prev
    Next
    INDEX
    Explanations

    ice-related compound words

    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
    ”
    -3.31
    </h2>
    -2.98
    <em>
    -2.84
    .”
    -2.75
    (
    -2.59
    <i>
    -2.55
     to
    -2.52
    <strong>
    -2.52
    </sup>
    -2.50
     希望
    -2.33
    POSITIVE LOGITS
    Manfaat
    2.70
     aktive
    2.66
    ilustrasi
    2.64
    Bukan
    2.58
    Kedua
    2.52
     bilde
    2.44
     är
    2.44
    Kondisi
    2.41
     différentes
    2.39
     amerikan
    2.38
    Activations Density 0.013%

    No Known Activations