© 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. 2701
    Prev
    Next
    INDEX
    Explanations

    http or https

    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
    //};
    -0.77
     Raja
    -0.71
     Zá
    -0.70
     について
    -0.69
    stech
    -0.68
     ihrem
    -0.68
    そこまで
    -0.67
    ulants
    -0.67
     المهم
    -0.66
     TOT
    -0.65
    POSITIVE LOGITS
    ीड
    0.76
    矶
    0.70
     ešte
    0.69
     Lilac
    0.68
    vartheta
    0.68
     hooked
    0.66
    bomber
    0.66
     Horticultural
    0.65
    jardin
    0.65
    aki
    0.65
    Activations Density 0.056%

    No Known Activations