© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85308
    Prev
    Next
    INDEX
    Explanations

    email subject lines

    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
     sò
    -1.50
     tè
    -1.36
     тоже
    -1.36
     pè
    -1.33
     contrario
    -1.33
    complish
    -1.32
     was
    -1.31
     noite
    -1.30
    want
    -1.30
    would
    -1.30
    POSITIVE LOGITS
    𝘬
    1.63
     about
    1.61
     Using
    1.52
     Combining
    1.52
     Having
    1.49
     Essentially
    1.45
     Normally
    1.44
     ensayo
    1.43
     Combined
    1.41
     ряда
    1.38
    Activations Density 0.016%

    No Known Activations