© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36345
    Prev
    Next
    INDEX
    Explanations

    by or from followed by agent

    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
    $$$
    -1.16
    (/^
    -1.13
    meisters
    -1.11
    
    -1.08
     access
    -1.08
    preneur
    -1.07
    >>>>
    -1.06
    ste
    -1.06
    this
    -1.04
    strator
    -1.04
    POSITIVE LOGITS
     someone
    2.14
     people
    1.70
     somebody
    1.65
     Können
    1.45
     a
    1.37
     también
    1.37
     dekol
    1.35
     who
    1.34
     mêmes
    1.32
    jaket
    1.31
    Activations Density 0.042%

    No Known Activations