© 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. 873
    Prev
    Next
    INDEX
    Explanations

    English speakers

    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
    設備
    0.29
     included
    0.27
     assistive
    0.26
     utilizing
    0.26
    A
    0.26
    <code>
    0.26
     KDE
    0.26
     In
    0.26
     utilize
    0.25
     Overall
    0.25
    POSITIVE LOGITS
     pensamento
    0.27
    ឬ
    0.27
     wład
    0.27
     یا
    0.26
     economist
    0.26
     menulis
    0.26
     besar
    0.25
     друзей
    0.25
     membentuk
    0.25
    ังสือ
    0.25
    Activations Density 0.000%

    No Known Activations