© 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. 109399
    Prev
    Next
    INDEX
    Explanations

    waste, repairs, warrants

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

    command punctuation and structure

    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
    regions
    0.48
    i
    0.47
    綺麗な
    0.45
    水
    0.43
    ی
    0.43
    fc
    0.43
    孝
    0.43
    falls
    0.42
    igungs
    0.42
    percent
    0.42
    POSITIVE LOGITS
     প্রসঙ্গ
    0.47
    🖐
    0.47
     બદ
    0.45
    🦊
    0.45
     Đó
    0.44
     বদলে
    0.44
     ।।
    0.44
     Replacing
    0.44
    摒
    0.43
     Амери
    0.42
    Activations Density 0.002%

    No Known Activations