© 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. 257352
    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
    用い
    0.51
    族
    0.48
    츨
    0.47
    τ
    0.46
    STEIN
    0.45
    ̠
    0.44
    וי
    0.43
    윳
    0.43
    Miranda
    0.42
     ლ
    0.41
    POSITIVE LOGITS
     decomposition
    0.54
     hypothetical
    0.53
     predetermined
    0.53
    पना
    0.52
     decomposed
    0.52
     attempting
    0.51
     encouraging
    0.51
     doable
    0.50
     promoting
    0.49
     möglichen
    0.49
    Activations Density 0.001%

    No Known Activations