© 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. 1413
    Prev
    Next
    INDEX
    Explanations

    об and Della

    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
    quartz
    -0.84
     Accesorios
    -0.81
    flüge
    -0.79
     vierten
    -0.77
    پایی
    -0.77
     einzigartigen
    -0.75
     locks
    -0.74
     Goodness
    -0.73
    uerto
    -0.73
     elongated
    -0.73
    POSITIVE LOGITS
     об
    0.81
     laps
    0.79
     Testa
    0.75
     doppel
    0.68
     说
    0.68
    lap
    0.68
     പ
    0.68
     thảo
    0.67
    ந்து
    0.67
    ．
    0.67
    Activations Density 0.036%

    No Known Activations