© 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. 92680
    Prev
    Next
    INDEX
    Explanations

    names preceded by Kim

    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
    -?
    -0.81
    difficulty
    -0.79
     fost
    -0.78
     بلند
    -0.73
     lilla
    -0.73
     Tengo
    -0.72
     Conce
    -0.70
    Quasi
    -0.70
    heran
    -0.69
     bubble
    -0.69
    POSITIVE LOGITS
    жнему
    0.81
    ⓥ
    0.80
    contenido
    0.79
    antal
    0.76
     tactile
    0.75
    CFU
    0.74
    onique
    0.73
     ti
    0.73
    面上
    0.73
    鎬
    0.73
    Activations Density 0.027%

    No Known Activations