© 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. 110749
    Prev
    Next
    INDEX
    Explanations

    driver, mixed-mode, Q, CIS, code, class

    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
    佩
    -0.73
     хоче
    -0.70
     any
    -0.70
    メニューは
    -0.69
     high
    -0.69
     hub
    -0.68
    担
    -0.68
     addressing
    -0.68
    沁
    -0.67
    ünchen
    -0.66
    POSITIVE LOGITS
    ywna
    0.94
     код
    0.89
     RTX
    0.84
     类
    0.84
    Captain
    0.83
    Quando
    0.82
    让自己
    0.81
    tiennent
    0.81
     PCS
    0.80
    ˮ
    0.80
    Activations Density 0.004%

    No Known Activations