© 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. 17494
    Prev
    Next
    INDEX
    Explanations

    link or post content

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

    points to, cause, axes

    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
     любого
    0.54
     normalen
    0.46
     අවශ්‍ය
    0.45
     आपण
    0.45
     любы
    0.45
     সীমাবদ্ধ
    0.45
     necesarios
    0.44
    眽
    0.44
     निर्धारित
    0.44
     normales
    0.44
    POSITIVE LOGITS
    чі
    0.48
     trousers
    0.44
    居然
    0.44
     διε
    0.41
     قتل
    0.40
     reportedly
    0.40
     δεί
    0.40
    魚
    0.39
     jīn
    0.38
    燬
    0.38
    Activations Density 0.001%

    No Known Activations