© 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. 208983
    Prev
    Next
    INDEX
    Explanations

    churches have tried

    np_acts-logits-general · gemini-2.5-flash-lite

    lists and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    컥
    0.52
    XPATH
    0.50
    쁠
    0.50
    Xr
    0.50
     படத்தை
    0.49
    шенные
    0.48
    bě
    0.48
     pozw
    0.48
    awcy
    0.48
     ಒತ್ತ
    0.47
    POSITIVE LOGITS
     l
    0.56
     n
    0.56
    ل
    0.52
     v
    0.51
     d
    0.50
     science
    0.50
     si
    0.49
     user
    0.49
     de
    0.48
     y
    0.48
    Activations Density 0.000%

    No Known Activations