© 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. 252515
    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
    ⟋
    0.49
    itteln
    0.47
    ürdig
    0.47
    いため
    0.47
    ätzung
    0.47
    etry
    0.46
    τικού
    0.46
    啠
    0.46
    abbanti
    0.46
    യുള്ള
    0.45
    POSITIVE LOGITS
    ud
    0.56
     esfuerzo
    0.47
     WORD
    0.45
     white
    0.44
     THAN
    0.44
     STUDENTS
    0.44
    ما
    0.43
     load
    0.43
     BOC
    0.43
    load
    0.43
    Activations Density 0.000%

    No Known Activations