© 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. 255080
    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
    रियो
    0.51
    ించారు
    0.49
     disclaimer
    0.49
    拉
    0.45
    ління
    0.45
    ல்லை
    0.44
    离
    0.44
    Mobs
    0.43
    珲
    0.43
    如果是
    0.43
    POSITIVE LOGITS
     Corp
    0.59
     romana
    0.50
     Perempuan
    0.49
     CORP
    0.48
     Thee
    0.47
     koniec
    0.46
    θρω
    0.44
    سرائيل
    0.43
     Rusia
    0.42
     Ñ
    0.42
    Activations Density 0.001%

    No Known Activations