© 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. 22-GEMMASCOPE-RES-131K
    7. 25788
    Prev
    Next
    INDEX
    Explanations

    Read more

    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_22/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
     strengthens
    -0.96
     usarlo
    -0.96
    ổ
    -0.95
     Phrases
    -0.89
     låg
    -0.89
    ሪ
    -0.88
     reschedule
    -0.88
     compró
    -0.88
     Lair
    -0.88
     särskilt
    -0.87
    POSITIVE LOGITS
    dades
    0.90
     [
    0.82
     r
    0.82
    contracts
    0.80
    xi
    0.79
     Wang
    0.78
     ts
    0.77
     Veränderungen
    0.77
    erson
    0.77
     experimental
    0.76
    Activations Density 0.036%

    No Known Activations