© 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. 57227
    Prev
    Next
    INDEX
    Explanations

    and even creating

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

    surgical technique, gaming news, singlehood

    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
     supernat
    0.51
    겟
    0.49
    ক্লো
    0.48
     পাবে
    0.48
    έσ
    0.48
    앱
    0.48
    အောင်
    0.47
    শিব
    0.47
     Golub
    0.46
    룀
    0.46
    POSITIVE LOGITS
    ild
    0.57
    ons
    0.46
     shoving
    0.45
    ane
    0.45
     مواليد
    0.44
    ali
    0.44
    ve
    0.44
     und
    0.44
    urs
    0.44
     fluids
    0.44
    Activations Density 0.000%

    No Known Activations