© 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. 258343
    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
    d
    0.46
    Js
    0.44
     bilge
    0.44
     J
    0.42
    then
    0.42
    jections
    0.41
    0.41
    ation
    0.40
    transformation
    0.40
    akuwa
    0.40
    POSITIVE LOGITS
    ৤
    0.59
     stehen
    0.57
     কর্নে
    0.57
    كان
    0.54
    <unused582>
    0.54
     ফর্ম
    0.53
     einige
    0.51
     অপারে
    0.51
     manchmal
    0.51
     entrambe
    0.51
    Activations Density 0.000%

    No Known Activations