© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27370
    Prev
    Next
    INDEX
    Explanations

    use_ or use- modules

    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_40_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
     experiencia
    0.38
    ogonal
    0.38
    ownicy
    0.38
    叠
    0.38
     দখল
    0.37
    疊
    0.37
    beni
    0.37
     hoteles
    0.37
    ვილი
    0.36
     hMut
    0.36
    POSITIVE LOGITS
     сроки
    0.41
    стана
    0.39
    猾
    0.38
     CIN
    0.38
    сү
    0.38
     timezone
    0.38
     Rays
    0.37
     आगामी
    0.37
    asco
    0.36
     ус
    0.36
    Activations Density 0.000%

    No Known Activations