© 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. 99184
    Prev
    Next
    INDEX
    Explanations

    website code or data

    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
     of
    -2.70
     jego
    -1.57
     incluyendo
    -1.55
    玙
    -1.38
    嬷
    -1.33
    étaro
    -1.28
     efekty
    -1.26
     Veränder
    -1.25
    ppincott
    -1.23
     dengan
    -1.22
    POSITIVE LOGITS
     fatale
    1.66
     mentale
    1.59
     latine
    1.55
     arbeitet
    1.52
    OOOOO
    1.48
     honn
    1.42
     potes
    1.42
     volon
    1.40
     maraming
    1.38
    _
    1.38
    Activations Density 0.057%

    No Known Activations