© 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-65K
    7. 2194
    Prev
    Next
    INDEX
    Explanations

    trading, war, map, bait, ship

    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_65k_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
    4
    0.89
    If
    0.66
    I
    0.65
    6
    0.65
    BackgroundColor
    0.63
    Encycl
    0.61
    3
    0.61
    TreeClassifier
    0.61
    [^
    0.60
    7
    0.59
    POSITIVE LOGITS
     for
    1.17
    n
    1.16
    ي
    0.96
    s
    0.92
    an
    0.89
    el
    0.88
    en
    0.85
     the
    0.85
    น
    0.84
     an
    0.83
    Activations Density 2.282%

    No Known Activations