© 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. 159717
    Prev
    Next
    INDEX
    Explanations

    barley grass

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

    elements, file, code, lists

    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
     كمان
    0.45
    ቖ
    0.45
     базу
    0.44
    раў
    0.44
     Потом
    0.43
    єдна
    0.42
    玖
    0.42
    يروس
    0.42
     octagon
    0.42
    صميم
    0.41
    POSITIVE LOGITS
     mengenai
    0.48
     permittivity
    0.48
     Chile
    0.45
    㳡
    0.45
     lö
    0.44
     misog
    0.44
     toit
    0.44
     acerca
    0.43
     här
    0.43
    azolin
    0.43
    Activations Density 0.000%

    No Known Activations