© 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. 138880
    Prev
    Next
    INDEX
    Explanations

    listing items in a series

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

    instructions or generating output

    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
     which
    0.53
    삼성
    0.46
    0
    0.46
     of
    0.46
    بی
    0.45
    晧
    0.44
     the
    0.43
    ത
    0.43
    <!
    0.43
     exemples
    0.43
    POSITIVE LOGITS
     തുടർ
    0.49
    缓冲
    0.47
     psal
    0.47
    Imidazole
    0.46
    ução
    0.46
    utuskan
    0.46
     संधि
    0.45
     igreja
    0.45
     ফ্যা
    0.45
     религи
    0.45
    Activations Density 0.001%

    No Known Activations