© 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. 34-GEMMASCOPE-RES-131K
    4. 53954
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and derivations

    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_34/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
     minder
    -0.97
     aktiviert
    -0.91
     cotta
    -0.91
     botas
    -0.91
    ―――
    -0.90
     Vieux
    -0.89
    editForm
    -0.89
     décisions
    -0.89
    IPL
    -0.88
     sprend
    -0.86
    POSITIVE LOGITS
     in
    0.87
    umable
    0.83
     па
    0.83
     spousal
    0.79
     někter
    0.79
     [
    0.77
    ><
    0.77
    fully
    0.77
    unnitel
    0.76
    devtools
    0.76
    Activations Density 0.075%

    No Known Activations