© 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. 254944
    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
    癒
    0.49
    <0xB4>
    0.46
    䡈
    0.44
     statunitense
    0.44
    UnaryOperation
    0.43
    ત્મક
    0.42
     expiresIn
    0.42
    Categorie
    0.42
    絴
    0.41
    بيه
    0.41
    POSITIVE LOGITS
     этих
    0.44
     Ethanol
    0.44
     dessas
    0.44
     خی
    0.43
     honors
    0.42
     Vect
    0.42
     Gut
    0.41
     জানার
    0.41
     Expect
    0.41
    اہ
    0.40
    Activations Density 0.000%

    No Known Activations