© 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. 164721
    Prev
    Next
    INDEX
    Explanations

    yours future

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

    linear map

    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
    r
    0.53
    Andre
    0.50
    Kend
    0.50
    Wil
    0.48
    Sydney
    0.48
    ни
    0.48
    Grace
    0.47
    Hamilton
    0.47
    Jackie
    0.47
    *.
    0.46
    POSITIVE LOGITS
     privé
    0.57
     restrooms
    0.53
     plufieurs
    0.53
     peasants
    0.51
     connexes
    0.50
     misfortunes
    0.50
     tradeoffs
    0.49
     monotony
    0.49
     transparence
    0.49
     addictions
    0.49
    Activations Density 0.001%

    No Known Activations