© 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. 127023
    Prev
    Next
    INDEX
    Explanations

    list items

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

    function returns test reporting fluid

    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
     heures
    0.52
     канали
    0.49
    FormParams
    0.48
    DropDownList
    0.48
    TextArea
    0.47
    洏
    0.47
    ਮ
    0.46
    缛
    0.46
    Expire
    0.46
    PasswordField
    0.46
    POSITIVE LOGITS
     -
    0.44
    ..\
    0.41
     Khr
    0.40
    atan
    0.40
     सुन
    0.40
    zv
    0.40
     Peace
    0.40
     sly
    0.39
    و
    0.39
    .“
    0.39
    Activations Density 0.001%

    No Known Activations