© 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. 36627
    Prev
    Next
    INDEX
    Explanations

    BTL abbreviation, chilled holding, custom assemblies

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

    systems, current, edge, toes

    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
    ۶
    0.48
     Vous
    0.46
     affair
    0.46
     sauf
    0.45
     ETA
    0.44
     et
    0.44
    effet
    0.44
     SANT
    0.44
    uper
    0.43
     remarquable
    0.43
    POSITIVE LOGITS
    谍
    0.54
    вери
    0.51
     mattis
    0.48
    洳
    0.46
    太多
    0.46
    原料
    0.44
    количество
    0.44
    替换
    0.44
    ృష్ణ
    0.44
     mozz
    0.44
    Activations Density 0.000%

    No Known Activations