© 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. 49369
    Prev
    Next
    INDEX
    Explanations

    interpreter reads and executes

    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
    t
    1.63
    i
    1.21
    h
    1.18
    ه
    1.16
     venezol
    1.13
    est
    1.05
    ekan
    1.05
    ре
    1.03
    a
    1.02
    ا
    1.01
    POSITIVE LOGITS
     interpreter
    0.96
    দের
    0.94
    the
    0.93
    মূলক
    0.91
    ých
    0.83
    이지만
    0.82
    이었다
    0.81
    ግሎ
    0.80
     Interpre
    0.76
     the
    0.75
    Activations Density 0.004%

    No Known Activations