© 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. 110147
    Prev
    Next
    INDEX
    Explanations

    restored stampinginterests pursuedSurefireReporter

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

    declarations of war

    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
    ().
    0.50
    Ic
    0.49
    ни
    0.49
    Tatar
    0.48
    mostly
    0.47
    ^*_{
    0.46
    mıştır
    0.46
    glClear
    0.46
     अलै
    0.46
    lama
    0.45
    POSITIVE LOGITS
     activate
    0.48
    ق
    0.43
     brag
    0.43
    সংস
    0.42
     employing
    0.42
    udsman
    0.41
     ایک
    0.41
    ――
    0.41
     activating
    0.41
    上半
    0.41
    Activations Density 0.000%

    No Known Activations