© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12479
    Prev
    Next
    INDEX
    Explanations

    one or more

    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_40_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
    bourne
    0.40
    bim
    0.39
    being
    0.38
    essere
    0.38
    has
    0.37
    can
    0.37
    substring
    0.37
    <unused50>
    0.36
    display
    0.35
    causing
    0.35
    POSITIVE LOGITS
     மேற்பட்ட
    0.60
     more
    0.56
     preferably
    0.51
     ከዚያ
    0.51
     hơn
    0.50
    以上的
    0.47
     maybe
    0.43
     arguably
    0.43
     many
    0.43
     dozens
    0.43
    Activations Density 0.030%

    No Known Activations