© 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. 78131
    Prev
    Next
    INDEX
    Explanations

    academic citations and links

    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
    axy
    -0.89
    nost
    -0.84
    dė
    -0.78
    phins
    -0.77
    otis
    -0.73
     Met
    -0.71
     sahi
    -0.70
    ссажи
    -0.70
     braid
    -0.69
     Leigh
    -0.69
    POSITIVE LOGITS
     BMC
    1.54
    BMC
    1.48
    ᅟ
    0.89
    ArrayList
    0.79
     démo
    0.78
    Springer
    0.76
    Açık
    0.75
    zdjęcie
    0.75
    pantalón
    0.74
     coûte
    0.72
    Activations Density 0.065%

    No Known Activations