© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4102
    Prev
    Next
    INDEX
    Explanations

    numbered lists after numbers or "US"

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

    alternatives and exceptions

    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_53_width_65k_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
     Vineyard
    0.35
     Planet
    0.33
     ​
    0.32
     Niveau
    0.32
    .​
    0.31
     Grassmann
    0.30
     Primero
    0.29
     Niet
    0.29
    ​,
    0.29
     Pens
    0.29
    POSITIVE LOGITS
    zeb
    0.34
    projectlombok
    0.33
    hehe
    0.30
    vere
    0.29
    endet
    0.29
    hubungan
    0.29
    ដ៏
    0.29
    zmq
    0.29
    avent
    0.28
    ShaderProgram
    0.28
    Activations Density 0.022%

    No Known Activations