© 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. 65904
    Prev
    Next
    INDEX
    Explanations

    document proudly

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

    ethnic background South Carolina

    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
    EL
    0.56
    of
    0.55
     wyróż
    0.52
    N
    0.51
    Y
    0.51
    l
    0.50
    LA
    0.50
    V
    0.50
    al
    0.50
    IS
    0.49
    POSITIVE LOGITS
    䆔
    0.58
     lf
    0.47
    드가
    0.46
    య్యా
    0.46
     معم
    0.45
     మా
    0.44
     स्टोक्स
    0.44
     Aya
    0.44
    珹
    0.44
     මා
    0.44
    Activations Density 0.000%

    No Known Activations