© 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. 48248
    Prev
    Next
    INDEX
    Explanations

    xml format

    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
    को
    0.65
    위
    0.65
    8
    0.64
     wigs
    0.64
    众
    0.64
    ी
    0.63
     има
    0.61
    ８
    0.61
    utiérrez
    0.61
    сет
    0.61
    POSITIVE LOGITS
     I
    0.80
     Brazilian
    0.71
     Lagrangian
    0.70
     M
    0.70
     Bayesian
    0.70
     Italian
    0.69
     F
    0.67
     Turkish
    0.66
     Qa
    0.66
     Peanut
    0.63
    Activations Density 0.001%

    No Known Activations