© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 257910
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    v
    0.54
    w
    0.47
    r
    0.45
    function
    0.45
    ន្ល
    0.44
    iji
    0.43
    უტ
    0.43
    var
    0.43
     convened
    0.43
    患
    0.43
    POSITIVE LOGITS
     التن
    0.44
     அம்
    0.43
     يش
    0.42
     respeto
    0.42
    lichkeit
    0.42
     Иль
    0.42
     mengungkapkan
    0.41
     cảm
    0.41
     aspetto
    0.41
     sentire
    0.41
    Activations Density 0.000%

    No Known Activations