© 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. 34219
    Prev
    Next
    INDEX
    Explanations

    GUI application framework

    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
     ];
    0.38
     conventions
    0.37
     {:
    0.35
     सिद्धि
    0.35
    йде
    0.34
     бур
    0.34
    l
    0.34
     .
    0.33
    decorators
    0.33
     Conventions
    0.33
    POSITIVE LOGITS
     montagne
    0.39
    立った
    0.38
    ینی
    0.36
    скохозяй
    0.36
    ческого
    0.35
     તેણે
    0.35
    Selected
    0.35
    ভারে
    0.34
    InputNum
    0.34
    Near
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.