© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39682
    Prev
    Next
    INDEX
    Explanations

    technical terms and code definitions

    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
     what
    -1.31
     and
    -1.13
    كات
    -1.01
     on
    -1.00
     Create
    -1.00
    Both
    -0.99
     or
    -0.98
     Normally
    -0.97
     Both
    -0.97
    jā
    -0.96
    POSITIVE LOGITS
     also
    1.37
     vitamine
    1.35
     salade
    1.16
     recomiendo
    1.13
    は
    1.08
     torta
    1.05
    änning
    1.03
    czegó
    1.02
     WELFARE
    1.02
     mues
    1.02
    Activations Density 0.001%

    No Known Activations