© 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. 240590
    Prev
    Next
    INDEX
    Explanations

    preparation to obtain

    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
     Image
    0.52
     আরও
    0.48
     unlikely
    0.48
     আরো
    0.48
    plementation
    0.47
    ప్ర
    0.46
    chester
    0.45
     प
    0.44
     উল্লেখ
    0.42
    Image
    0.42
    POSITIVE LOGITS
    カラム
    0.53
     tablette
    0.50
    変数
    0.48
    ين
    0.47
     çerçe
    0.47
    čním
    0.46
     payee
    0.46
     মূল্যবান
    0.46
     cadena
    0.46
     enseñanzas
    0.46
    Activations Density 0.001%

    No Known Activations