© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208867
    Prev
    Next
    INDEX
    Explanations

    all donors and messages

    np_acts-logits-general · gemini-2.5-flash-lite

    label stock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genes
    0.53
     fund
    0.50
    ॉम
    0.49
     tabs
    0.48
     posao
    0.48
    Learn
    0.48
     naming
    0.47
    1
    0.46
     curr
    0.46
     genetics
    0.46
    POSITIVE LOGITS
    akkhati
    0.44
     긴
    0.44
    iyordu
    0.44
     निश्चित
    0.44
    ថ្ងៃ
    0.43
    avises
    0.43
     emphasises
    0.42
     оре
    0.41
    isiert
    0.41
     حتی
    0.41
    Activations Density 0.000%

    No Known Activations