© 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. 90572
    Prev
    Next
    INDEX
    Explanations

    specific locations and technical terms

    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
     détente
    -0.85
     Lorca
    -0.77
    杓
    -0.76
     Herder
    -0.73
    མ
    -0.71
    GestureDetector
    -0.70
    🍇
    -0.70
     cardia
    -0.70
    gång
    -0.69
    volles
    -0.69
    POSITIVE LOGITS
     Half
    0.91
     Daly
    0.79
    sip
    0.77
    abinieri
    0.75
     Devil
    0.74
    bf
    0.70
     Brisbane
    0.69
     évêque
    0.69
    PMG
    0.69
    stopping
    0.68
    Activations Density 0.028%

    No Known Activations