© 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. 218830
    Prev
    Next
    INDEX
    Explanations

    lists of items or specifications

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

    from Python

    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
    ъ
    0.52
    运营
    0.51
    рай
    0.50
     despicable
    0.48
     párrafo
    0.48
    ั
    0.48
    家人
    0.47
    วม
    0.46
     comodidad
    0.46
    舒適
    0.46
    POSITIVE LOGITS
     perde
    0.44
    Oke
    0.42
     ایر
    0.41
     하게
    0.41
    alike
    0.41
    Raster
    0.40
     thủy
    0.40
    jets
    0.40
     niewiel
    0.40
    Framebuffer
    0.39
    Activations Density 0.001%

    No Known Activations