© 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-262K
    7. 43695
    Prev
    Next
    INDEX
    Explanations

    hyperbolic geometry and ABC notation

    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
    dır
    0.63
    daftar
    0.61
     விளங்க
    0.60
    grupo
    0.59
    di
    0.55
    ۳
    0.55
    dir
    0.54
    ков
    0.54
    docker
    0.54
    «.
    0.54
    POSITIVE LOGITS
     handlebars
    0.64
     independence
    0.61
     randon
    0.61
    oinen
    0.58
     getN
    0.56
     backtracking
    0.56
     getc
    0.56
    /
    0.54
     gener
    0.54
     motorcycle
    0.52
    Activations Density 0.000%

    No Known Activations