© 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. 77421
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     देता
    -0.81
     Abschnitt
    -0.77
    controllers
    -0.77
     quiser
    -0.76
    getSeconds
    -0.75
    tivi
    -0.74
    不见
    -0.73
     either
    -0.72
    balanceOf
    -0.71
    osp
    -0.71
    POSITIVE LOGITS
     intend
    0.79
     dessa
    0.78
    ülerin
    0.76
     icy
    0.76
    讹
    0.75
     pikiran
    0.73
     पर्
    0.73
     intends
    0.73
     fiables
    0.73
     ersten
    0.72
    Activations Density 0.015%

    No Known Activations