© 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. 72543
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
     Dette
    -1.23
    standes
    -1.06
    Уже
    -1.01
    readAs
    -1.01
     Saat
    -0.93
     Redewendung
    -0.93
     Durchführung
    -0.93
     SUCH
    -0.91
    蒟
    -0.90
    ╟
    -0.90
    POSITIVE LOGITS
     sorta
    1.04
     okay
    0.99
     suppose
    0.97
     obligado
    0.97
     say
    0.96
     tedavi
    0.94
     más
    0.94
     çöz
    0.94
     республики
    0.94
     everybody
    0.91
    Activations Density 0.037%

    No Known Activations