© 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. 256840
    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
     redundancies
    0.43
     लेक्चर
    0.40
    drawer
    0.40
     pap
    0.39
    垃圾
    0.38
    讨
    0.38
    龛
    0.38
    ativistic
    0.37
     papar
    0.37
    decorative
    0.37
    POSITIVE LOGITS
    yil
    0.53
     Piotr
    0.49
     Micha
    0.48
     исче
    0.48
    ી
    0.47
     همه
    0.46
     anastomosis
    0.45
    ా
    0.45
     werde
    0.45
    length
    0.45
    Activations Density 0.001%

    No Known Activations