© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166544
    Prev
    Next
    INDEX
    Explanations

    number types

    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
    📟
    0.38
     இயக்க
    0.36
    مہ
    0.36
    ادرات
    0.35
    Loading
    0.35
    ্রেট
    0.35
    >)`](
    0.34
    עד
    0.34
     நிறுவ
    0.34
    iativa
    0.33
    POSITIVE LOGITS
     потом
    0.46
     Потом
    0.37
     શરૂ
    0.36
     Beginning
    0.35
     начало
    0.35
     Posteriormente
    0.35
     सुरुवात
    0.35
    𝕤
    0.35
     چشم
    0.34
    >′
    0.34
    Activations Density 0.123%

    No Known Activations