© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98347
    Prev
    Next
    INDEX
    Explanations

    html anchors

    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
     Bloomfield
    -0.70
     levels
    -0.70
    unjukkan
    -0.69
     level
    -0.68
     торт
    -0.65
     downt
    -0.64
    看護
    -0.64
     уровня
    -0.64
    .__
    -0.64
    花园
    -0.63
    POSITIVE LOGITS
     jsonArray
    0.68
    教授
    0.68
     Sutter
    0.66
    rapnel
    0.66
    wot
    0.65
     heet
    0.65
     Lothar
    0.64
     Herzegovina
    0.62
     hoje
    0.62
     dessin
    0.62
    Activations Density 0.045%

    No Known Activations