© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3276
    Prev
    Next
    INDEX
    Explanations

    names and endings like 'per' or 'oper'

    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
    timbangan
    -1.00
    StringBuffer
    -0.80
    щет
    -0.73
    tempuran
    -0.72
    Drying
    -0.72
    labeling
    -0.69
     otherwise
    -0.68
    xty
    -0.66
    gerakan
    -0.66
    氵
    -0.66
    POSITIVE LOGITS
    OPER
    0.93
    aper
    0.92
    thwaite
    0.83
    lru
    0.81
     apresenta
    0.79
    提出
    0.78
    چال
    0.77
    olateral
    0.77
    Память
    0.76
    会议
    0.76
    Activations Density 0.050%

    No Known Activations