© 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. 107081
    Prev
    Next
    INDEX
    Explanations

    ifndef COMPONENTS headers

    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
    anap
    -0.80
     incomp
    -0.77
    奢侈
    -0.74
    oggle
    -0.71
    acti
    -0.71
     scru
    -0.69
     Rov
    -0.69
     Joo
    -0.68
    кси
    -0.68
    脅
    -0.68
    POSITIVE LOGITS
     Chromium
    0.99
     Chrome
    0.82
    iree
    0.81
    agar
    0.79
    gyp
    0.77
    anstalt
    0.75
    laubt
    0.74
    Shaped
    0.70
    hua
    0.70
    Chrome
    0.69
    Activations Density 0.177%

    No Known Activations