© 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. 64239
    Prev
    Next
    INDEX
    Explanations

    gesture recogniser

    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
    laquo
    -0.81
    ellees
    -0.81
    父母
    -0.75
     Depth
    -0.71
     depth
    -0.71
    yao
    -0.71
    基本上
    -0.70
    hrs
    -0.70
     Coffin
    -0.70
    сте
    -0.69
    POSITIVE LOGITS
    𝟙
    0.80
    Idade
    0.79
    <0xDD>
    0.79
     miesto
    0.78
    定向
    0.76
     pièces
    0.75
    bilirsiniz
    0.75
    utet
    0.74
     дра
    0.73
    Chamber
    0.72
    Activations Density 0.003%

    No Known Activations