© 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. 45251
    Prev
    Next
    INDEX
    Explanations

    quite charming

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

    breaking down complex topics

    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
     प्रधान
    0.50
     >>
    0.50
    iliency
    0.48
    º
    0.46
     counselor
    0.44
    rightarrow
    0.44
     monetization
    0.44
     juror
    0.43
    ಿದ್ದಾರೆ
    0.43
    ренко
    0.43
    POSITIVE LOGITS
    鎿
    0.49
     Villar
    0.49
    isil
    0.48
    сів
    0.47
     Люди
    0.45
     arXiv
    0.45
    嶌
    0.45
    上限
    0.44
    傗
    0.44
     Lille
    0.44
    Activations Density 0.000%

    No Known Activations