© 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. 33468
    Prev
    Next
    INDEX
    Explanations

    company suffixes

    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
    orul
    -1.29
     teórico
    -1.16
     aktual
    -1.16
     çünkü
    -1.14
     allerlei
    -1.13
    decken
    -1.13
     pengar
    -1.13
    tyy
    -1.12
    =*
    -1.11
    来不及
    -1.11
    POSITIVE LOGITS
     It
    1.23
    у
    1.14
     not
    1.13
     There
    1.13
     family
    1.12
     children
    1.12
     there
    1.10
     Although
    1.09
     still
    1.04
     fortfarande
    1.02
    Activations Density 0.015%

    No Known Activations