© 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. 259600
    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
     dilemma
    0.46
     edema
    0.46
    ocaust
    0.46
    ά
    0.46
     глю
    0.45
     HAVING
    0.45
     entwickeln
    0.44
    ীতি
    0.44
     них
    0.44
     semicircle
    0.44
    POSITIVE LOGITS
    abby
    0.44
    jz
    0.44
    z
    0.43
     Old
    0.42
    火
    0.42
    消防
    0.41
     Dirty
    0.41
     reads
    0.41
    uj
    0.40
    एलबी
    0.40
    Activations Density 0.001%

    No Known Activations