© 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. 255957
    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
    0
    0.55
    у
    0.54
     Tind
    0.44
    ο
    0.44
    ᅧ
    0.44
    ре
    0.42
    на
    0.41
    وم
    0.41
    о
    0.41
    Seven
    0.40
    POSITIVE LOGITS
     BUFFER
    0.57
     общество
    0.55
     printr
    0.54
     он
    0.54
    กระท
    0.54
     หน้า
    0.52
     వ్యా
    0.51
     вектор
    0.51
     они
    0.51
     прода
    0.50
    Activations Density 0.000%

    No Known Activations