© 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. 218254
    Prev
    Next
    INDEX
    Explanations

    repair information

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

    difficult themes or thoughts

    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
    ლ
    0.54
    нул
    0.48
    鐙
    0.48
    出的
    0.47
     Consequently
    0.47
    鈮
    0.47
    不過
    0.46
     কর্মকর্তা
    0.45
    點
    0.45
    ᆻ
    0.45
    POSITIVE LOGITS
     tavern
    0.54
     taver
    0.49
     devez
    0.48
     downloads
    0.48
     citation
    0.47
     citations
    0.46
    tavern
    0.46
     oe
    0.46
     california
    0.46
     reborn
    0.46
    Activations Density 0.000%

    No Known Activations