© 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. 118573
    Prev
    Next
    INDEX
    Explanations

    copyright or license

    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
    geb
    -0.81
    ATUS
    -0.71
     Specialty
    -0.69
     Oba
    -0.69
    Eb
    -0.68
     hundred
    -0.68
    cb
    -0.67
     Heap
    -0.66
    RED
    -0.65
     Benjamin
    -0.65
    POSITIVE LOGITS
    Tanggal
    0.85
    詫
    0.69
    onthe
    0.68
     فرص
    0.67
     mirada
    0.66
     Mindy
    0.66
     Ön
    0.65
     iterate
    0.65
    vou
    0.65
     đáng
    0.64
    Activations Density 0.488%

    No Known Activations