© 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. 6805
    Prev
    Next
    INDEX
    Explanations

    code metadata

    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
    ಿದೆ
    -0.71
    $('.
    -0.69
     Applies
    -0.68
    Jep
    -0.67
     Attic
    -0.65
     Satellites
    -0.65
    titian
    -0.65
     Adolescent
    -0.65
     онъ
    -0.63
     gubern
    -0.63
    POSITIVE LOGITS
     Moreno
    0.83
     مع
    0.79
     yanı
    0.77
    ре
    0.76
     Rodrigo
    0.74
     mỗi
    0.74
    onChangeText
    0.73
     Resort
    0.73
    volume
    0.73
    RE
    0.73
    Activations Density 0.577%

    No Known Activations