© 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. 256088
    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
     instrumentality
    0.42
    נען
    0.42
    Χ
    0.41
    ΕΙ
    0.40
     ordinarily
    0.40
    στά
    0.39
    Instrument
    0.39
     Instrument
    0.38
    是为了
    0.38
    将在
    0.38
    POSITIVE LOGITS
    odenum
    0.44
    umping
    0.44
    ufact
    0.43
    icitis
    0.43
    ജാ
    0.41
    тику
    0.41
     вниз
    0.40
    箋
    0.40
     дальше
    0.40
    チュア
    0.40
    Activations Density 0.006%

    No Known Activations