© 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. 89850
    Prev
    Next
    INDEX
    Explanations

    local laws

    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
     excitation
    0.52
     ch
    0.51
     EMA
    0.49
     ç
    0.48
     Chant
    0.48
     putative
    0.47
     Energ
    0.47
     CHP
    0.47
     bandas
    0.47
     transfer
    0.46
    POSITIVE LOGITS
    लु
    0.57
    ジ
    0.52
    น
    0.51
    )*((
    0.51
    कई
    0.50
    Valencia
    0.49
    Giá
    0.48
    nice
    0.48
    लिसिस
    0.48
    )*(
    0.48
    Activations Density 0.000%

    No Known Activations