© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 52394
    Prev
    Next
    INDEX
    Explanations

    Let us

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

    comparing choices or asking how

    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
     whakam
    0.45
    휙
    0.44
     embaixo
    0.43
     trenger
    0.42
    #
    0.42
    keyCode
    0.42
     illuminates
    0.41
     funcione
    0.41
     ainfi
    0.40
    ṃ
    0.40
    POSITIVE LOGITS
     ব্যবসায়
    0.50
     ব্যবসায়
    0.47
     تجارت
    0.44
     Birthday
    0.42
     مدرسه
    0.40
     他们
    0.40
    તાઓ
    0.40
     ঘনিষ্ঠ
    0.40
     স্কুলে
    0.40
     売
    0.39
    Activations Density 0.000%

    No Known Activations