Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 20061
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and calculations

    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
     تقریباً
    0.42
     ප
    0.40
     சுமார்
    0.40
     सुमारे
    0.39
    roughly
    0.38
     पचास
    0.37
     ಎರಡು
    0.36
    approximately
    0.35
     approx
    0.35
    兩
    0.35
    POSITIVE LOGITS
    Mixin
    0.39
     mismo
    0.39
    变得
    0.38
     stesse
    0.38
    та
    0.36
    堵
    0.35
     come
    0.35
     mismos
    0.35
     hush
    0.35
     vac
    0.34
    Activations Density 0.020%

    No Known Activations