© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116487
    Prev
    Next
    INDEX
    Explanations

    collection, storytelling, buildings

    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
     Seek
    -0.76
    룡
    -0.72
     getting
    -0.70
    བྱ
    -0.70
    AMES
    -0.70
    ไม้
    -0.69
     cling
    -0.69
    فاء
    -0.68
     history
    -0.67
    Seek
    -0.67
    POSITIVE LOGITS
    ント
    0.69
     Princes
    0.68
    wai
    0.67
     последнее
    0.66
    CTG
    0.66
     pure
    0.66
    wia
    0.66
    colección
    0.66
    ugges
    0.65
    تين
    0.65
    Activations Density 0.065%

    No Known Activations