© 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. 258259
    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
     ismi
    0.53
     توانائی
    0.50
     promete
    0.48
    岛
    0.47
     ali
    0.46
     necesariamente
    0.46
     simbolo
    0.46
    물
    0.46
     splice
    0.46
     ladr
    0.46
    POSITIVE LOGITS
    igungs
    0.50
    Handler
    0.49
    AppName
    0.46
    дка
    0.46
    ждены
    0.46
    Unlock
    0.46
    origData
    0.46
    Nurse
    0.46
    ců
    0.44
    ડિયા
    0.44
    Activations Density 0.000%

    No Known Activations