© 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. 97206
    Prev
    Next
    INDEX
    Explanations

    locations and films

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

    complex systems and phenomena

    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
     gid
    0.48
    artig
    0.46
     gericht
    0.46
    iót
    0.45
     coopération
    0.45
    uzen
    0.45
    內
    0.45
     heritage
    0.44
     والذي
    0.44
    ور
    0.43
    POSITIVE LOGITS
     স্যার
    0.45
     disimpan
    0.44
    asu
    0.44
     スカート
    0.42
     様
    0.42
    queleto
    0.42
     प्रभावशाली
    0.41
     அழு
    0.41
     とする
    0.41
    チェア
    0.40
    Activations Density 0.000%

    No Known Activations