© 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. 58081
    Prev
    Next
    INDEX
    Explanations

    mobile, stock, manager, tubing, original, step

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

    relax, self-care, mindfulness, personal development

    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
    oció
    0.52
     chhoti
    0.49
    nicheskij
    0.48
     jaaye
    0.48
     nemmeno
    0.47
     木
    0.47
    ান্তরে
    0.46
     recordó
    0.46
    kadang
    0.46
     Qualitäts
    0.45
    POSITIVE LOGITS
    া
    0.47
    珵
    0.46
    ্জ
    0.46
    ا
    0.45
    رة
    0.45
    ում
    0.45
     Warnings
    0.45
    是用
    0.44
     -
    0.43
    סה
    0.43
    Activations Density 0.000%

    No Known Activations