© 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. 123846
    Prev
    Next
    INDEX
    Explanations

    academic citations

    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
     peinados
    -1.67
    ",
    -1.63
     bolsillos
    -1.59
     and
    -1.48
    </h5>
    -1.48
    raszam
    -1.45
    </h1>
    -1.42
     also
    -1.41
     demostrar
    -1.39
     $^{
    -1.37
    POSITIVE LOGITS
     such
    1.59
     needing
    1.57
    荑
    1.55
    莚
    1.42
     these
    1.38
    は以下の
    1.38
    1
    1.35
     vehic
    1.32
     Notwendigkeit
    1.32
    cinoma
    1.30
    Activations Density 0.007%

    No Known Activations