© 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. 185895
    Prev
    Next
    INDEX
    Explanations

    neighborhoods, owners, deserves, combined effect, your router, move through, you are, November

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

    file handling and calculations

    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
    um
    0.52
    ui
    0.49
     né
    0.48
    ena
    0.47
    ifie
    0.47
    utian
    0.46
     네
    0.46
     αρ
    0.45
    öre
    0.45
    inda
    0.44
    POSITIVE LOGITS
     measurements
    0.51
     extremos
    0.50
     Suarez
    0.49
    چھا
    0.47
     mattresses
    0.47
     $.
    0.46
    ன்கள்
    0.46
     glycolysis
    0.45
     depriving
    0.44
    ாடி
    0.44
    Activations Density 0.000%

    No Known Activations