© 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. 238625
    Prev
    Next
    INDEX
    Explanations

    conference finals

    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
     দাবিতে
    0.45
    Institutional
    0.44
    economic
    0.43
     ដើម្បី
    0.42
    myapp
    0.42
    <unused1043>
    0.42
     pelayanan
    0.42
    🕖
    0.42
     учреждений
    0.41
     Centers
    0.41
    POSITIVE LOGITS
    (
    0.49
    代码
    0.46
     nuclear
    0.46
     olmadan
    0.44
    )))
    0.44
    COMMAND
    0.43
     repo
    0.42
     cmake
    0.42
    :",
    0.42
    _(
    0.41
    Activations Density 0.001%

    No Known Activations