© 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. 212995
    Prev
    Next
    INDEX
    Explanations

    requests or statements about families

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

    limiting research and innovation

    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
    ᙱ
    0.52
     directement
    0.48
     reck
    0.48
    ীকার
    0.47
    っいて
    0.47
     gak
    0.46
     droit
    0.46
     converters
    0.46
     trolls
    0.46
     devil
    0.46
    POSITIVE LOGITS
     Marks
    0.48
     Labels
    0.48
    res
    0.45
    的功能
    0.44
    拉
    0.43
    s
    0.43
    Type
    0.42
     XMLHttpRequest
    0.42
    hu
    0.41
    ester
    0.40
    Activations Density 0.000%

    No Known Activations