© 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. 1951
    Prev
    Next
    INDEX
    Explanations

    t-shirt mockup

    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
     spond
    0.66
     cations
    0.63
     chitin
    0.61
     سید
    0.61
    힛
    0.61
     chirop
    0.61
     tämän
    0.59
     cenderung
    0.59
     Solicitor
    0.58
     Superintendent
    0.57
    POSITIVE LOGITS
    t
    1.08
    il
    0.84
    j
    0.81
    shirts
    0.77
    shirt
    0.77
    ko
    0.76
    ar
    0.75
    ij
    0.75
    ير
    0.72
     camiseta
    0.72
    Activations Density 0.007%

    No Known Activations