© 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. 68866
    Prev
    Next
    INDEX
    Explanations

    Republican gerrymandering

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

    disapproving or approving

    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
     bandeja
    0.52
    墘
    0.51
     Horoscope
    0.49
     restaur
    0.46
     nir
    0.46
     hairline
    0.44
     Ramona
    0.44
     Edmond
    0.43
    ंटी
    0.43
     Supernatural
    0.43
    POSITIVE LOGITS
    n
    0.55
    p
    0.54
    eastern
    0.52
    mostly
    0.52
    Gs
    0.49
    g
    0.49
    extracted
    0.46
    pst
    0.46
    boosting
    0.46
    assembly
    0.46
    Activations Density 0.000%

    No Known Activations