© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 29722
    Prev
    Next
    INDEX
    Explanations

    dark circles under eyes

    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_16_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
    W
    0.61
    V
    0.59
     minimize
    0.59
     nächsten
    0.58
     leben
    0.58
    peror
    0.57
    蟆
    0.57
    ോഗ
    0.57
     إ
    0.57
    قال
    0.57
    POSITIVE LOGITS
     Allahabad
    0.58
     sinusoidal
    0.54
    ेंस
    0.50
     Украины
    0.49
     jangka
    0.49
     OBJECTTYPE
    0.48
     signification
    0.46
     Palmer
    0.46
     ホイール
    0.46
     증
    0.45
    Activations Density 0.002%

    No Known Activations