© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34418
    Prev
    Next
    INDEX
    Explanations

    out for

    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
    m
    0.81
     allong
    0.80
     اله
    0.77
    것
    0.75
    lang
    0.75
    بر
    0.73
     차지
    0.73
    𝓶
    0.71
    وم
    0.71
    uent
    0.71
    POSITIVE LOGITS
     can
    0.99
    :
    0.98
    ,
    0.97
     galvan
    0.97
     to
    0.89
     l
    0.89
     flamboyant
    0.88
     galvanized
    0.86
    ر
    0.83
    ವಾಗಿ
    0.82
    Activations Density 0.008%

    No Known Activations