© 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. 195656
    Prev
    Next
    INDEX
    Explanations

    words or other picture

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

    Cultural Significance, shared features, other planets

    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
     ELL
    0.46
     Sommers
    0.45
     BAFF
    0.44
     石
    0.44
     Hitch
    0.44
    不开
    0.44
     ఆట
    0.44
     DOG
    0.44
     通常
    0.44
    aların
    0.43
    POSITIVE LOGITS
    я
    0.54
    све
    0.49
    র্তি
    0.48
    лась
    0.47
     encontrar
    0.47
    갚
    0.47
    т
    0.47
    и
    0.46
    є
    0.46
     }^{
    0.46
    Activations Density 0.000%

    No Known Activations