© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57441
    Prev
    Next
    INDEX
    Explanations

    Santa Barbara, Valerie Ackley

    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
    嫵
    -0.84
    ついでに
    -0.77
     policemen
    -0.76
    chè
    -0.75
    됬
    -0.75
     quen
    -0.75
     Cultivation
    -0.74
     hij
    -0.74
     accumulations
    -0.71
     bootstra
    -0.71
    POSITIVE LOGITS
    dieren
    0.91
    glClear
    0.79
    Dry
    0.77
    DllImport
    0.75
    ModelAndView
    0.74
    SearchParams
    0.73
     dry
    0.72
    康
    0.71
    Mann
    0.71
    Paint
    0.71
    Activations Density 0.025%

    No Known Activations