© 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. 156878
    Prev
    Next
    INDEX
    Explanations

    Australia, now, shop

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

    ensure extra resources

    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
    ੯
    0.52
     ਜ
    0.47
    glomer
    0.47
    ОВ
    0.46
     ਵੀ
    0.45
    deviation
    0.45
    味が
    0.45
    ਜੀ
    0.44
     முழு
    0.44
    ಅ
    0.44
    POSITIVE LOGITS
     Gret
    0.46
     spouses
    0.45
     encuentran
    0.45
     Gifts
    0.45
     both
    0.44
     Dawkins
    0.43
    Payments
    0.43
     grads
    0.43
     siguiendo
    0.43
     uczni
    0.43
    Activations Density 0.000%

    No Known Activations