© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51599
    Prev
    Next
    INDEX
    Explanations

    advanced topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Faites
    0.53
     objet
    0.47
     dispara
    0.45
     ouvrage
    0.45
     avec
    0.45
     جوسینو
    0.44
     haute
    0.44
    <unused588>
    0.44
     OnInit
    0.44
    <unused681>
    0.43
    POSITIVE LOGITS
    inars
    0.51
    metal
    0.47
    elijkheid
    0.44
    ut
    0.44
    phere
    0.44
    ！”
    0.43
    rology
    0.43
    ায়ী
    0.43
     speakers
    0.43
    elin
    0.43
    Activations Density 0.000%

    No Known Activations