© 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. 41806
    Prev
    Next
    INDEX
    Explanations

    standard cilantro

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

    operations to perform

    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
    怅
    0.49
     ث
    0.48
     boroughs
    0.47
     voisines
    0.45
     désir
    0.45
     inwoners
    0.44
     propriétaires
    0.44
     cinqui
    0.43
    觎
    0.43
     మరింత
    0.42
    POSITIVE LOGITS
    body
    0.47
    inch
    0.45
    pump
    0.45
    paper
    0.45
    fusion
    0.43
    {&
    0.43
    switch
    0.43
    你要
    0.43
     транс
    0.43
     transmits
    0.43
    Activations Density 0.001%

    No Known Activations