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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93012
    Prev
    Next
    INDEX
    Explanations

    words following "its", "from", "coming"

    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
     nggak
    -0.73
     frequency
    -0.71
    olla
    -0.70
     comps
    -0.69
    司
    -0.68
    生徒
    -0.68
    squareup
    -0.67
     glass
    -0.66
    ירת
    -0.66
     wig
    -0.66
    POSITIVE LOGITS
     Bridges
    0.85
     Brücke
    0.80
     '.$
    0.79
    ättning
    0.79
     Ammonium
    0.78
    cast
    0.78
     Oct
    0.77
     Brücken
    0.77
     людини
    0.76
    絎
    0.75
    Activations Density 0.010%

    No Known Activations