© 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. 249108
    Prev
    Next
    INDEX
    Explanations

    business and official terms

    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
     своё
    0.48
    ات
    0.46
     সেজন্য
    0.45
    이랑
    0.45
    세
    0.44
    ласти
    0.43
     دائما
    0.43
    ۲
    0.43
    UES
    0.43
    ová
    0.43
    POSITIVE LOGITS
     Jamaica
    0.52
     Glasgow
    0.50
     we
    0.50
     Gon
    0.50
     Swansea
    0.49
     brid
    0.48
     Hi
    0.48
     hound
    0.48
     Gone
    0.47
     Ext
    0.47
    Activations Density 0.000%

    No Known Activations