© 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. 257415
    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
     Untersuchung
    0.45
     FIC
    0.44
     MEDIC
    0.43
     quaternion
    0.43
    ಸು
    0.42
     Fett
    0.42
     Kết
    0.42
    瞇
    0.41
     QUESTION
    0.41
    ষি
    0.41
    POSITIVE LOGITS
     생
    0.45
     생각
    0.45
     کاری
    0.45
    hatt
    0.44
    erah
    0.44
    uvu
    0.44
    outof
    0.43
     전류
    0.43
     pemilihan
    0.43
    opo
    0.43
    Activations Density 0.001%

    No Known Activations