© 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. 34-GEMMASCOPE-RES-131K
    7. 47986
    Prev
    Next
    INDEX
    Explanations

    mix or beat ingredients

    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
     Flüssigkeit
    -0.83
    گرم
    -0.82
     through
    -0.79
     to
    -0.76
     opzioni
    -0.75
    tries
    -0.73
    ppr
    -0.71
    rolls
    -0.70
    fluid
    -0.69
     sovereign
    -0.69
    POSITIVE LOGITS
     beat
    1.95
     Beat
    1.92
    Beat
    1.73
    beat
    1.60
     whipping
    1.58
     beating
    1.57
     whisk
    1.52
     whip
    1.51
     mixer
    1.43
     beater
    1.36
    Activations Density 0.007%

    No Known Activations