© 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. 631
    Prev
    Next
    INDEX
    Explanations

    area of shape

    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
     perdu
    -0.77
     signora
    -0.71
    Nacional
    -0.71
    ｦ
    -0.69
    gridColumn
    -0.69
    וף
    -0.68
     Istituto
    -0.67
    ッド
    -0.66
     COMMUNICATIONS
    -0.66
    ріш
    -0.66
    POSITIVE LOGITS
     shaped
    0.82
    SHAPE
    0.81
     modelos
    0.78
    вающая
    0.71
    hape
    0.71
     ald
    0.71
     شكل
    0.70
    izowane
    0.69
     DSS
    0.69
     revs
    0.69
    Activations Density 0.035%

    No Known Activations