© 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. 254755
    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
    hoon
    0.54
    f
    0.51
    jani
    0.50
    impl
    0.48
    zero
    0.47
    spl
    0.47
    gam
    0.47
    dan
    0.47
    Zero
    0.47
    Exec
    0.47
    POSITIVE LOGITS
     attano
    0.51
     COLLISIONS
    0.49
    衹
    0.49
    恢復
    0.48
     intimacy
    0.47
    นา
    0.46
    比起
    0.46
     berdoa
    0.45
     ڈال
    0.45
     necklaces
    0.45
    Activations Density 0.001%

    No Known Activations