© 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. 71244
    Prev
    Next
    INDEX
    Explanations

    device patterns

    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
     "
    -2.17
    (!__
    -2.11
    <td>
    -2.02
     was
    -1.95
     you
    -1.72
     -
    -1.66
     of
    -1.66
    there
    -1.63
     they
    -1.59
     for
    -1.58
    POSITIVE LOGITS
     guapos
    2.22
     informacje
    2.05
     raconter
    2.02
     segítség
    1.98
     PRODUCTO
    1.95
     renforcer
    1.95
    𒊹
    1.91
     contará
    1.90
    ⛤
    1.90
    𓆉
    1.86
    Activations Density 1.721%

    No Known Activations