© 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. 60736
    Prev
    Next
    INDEX
    Explanations

    words following specific terms

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

    questions starting with what why

    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
     Nick
    0.54
     Pines
    0.49
    Хо
    0.49
     Josh
    0.48
     Kiev
    0.48
     Q
    0.46
     lí
    0.46
     don
    0.46
     G
    0.44
     dey
    0.44
    POSITIVE LOGITS
    smittel
    0.48
    ulus
    0.48
    ώντας
    0.47
    ╼
    0.47
    kube
    0.47
     ως
    0.46
    ｖ
    0.45
     স্বরে
    0.44
    そこで
    0.44
    tede
    0.44
    Activations Density 0.000%

    No Known Activations