© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1740
    Prev
    Next
    INDEX
    Explanations

    Previous state or version

    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
     zu
    0.61
     cité
    0.59
     furent
    0.59
     questa
    0.59
     hacia
    0.59
    :”
    0.58
    ?»
    0.58
     in
    0.57
     cette
    0.57
     naar
    0.57
    POSITIVE LOGITS
     yourself
    0.62
    on
    0.59
     Yourself
    0.57
     دارید
    0.56
    y
    0.56
    n
    0.54
    гыз
    0.54
    몬
    0.53
    gies
    0.52
    ząt
    0.52
    Activations Density 0.099%

    No Known Activations