© 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. 53447
    Prev
    Next
    INDEX
    Explanations

    project completion details

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

    AttributeError, odor, share

    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
     undertakings
    0.46
    க்குப்
    0.46
    ຮ
    0.46
    އ
    0.45
    fundamentals
    0.44
     dependability
    0.44
    language
    0.44
    حظ
    0.44
    த
    0.43
    ösungen
    0.43
    POSITIVE LOGITS
     నేను
    0.47
    ্মা
    0.46
     pedibusque
    0.46
     meriye
    0.45
     মাসে
    0.45
     数
    0.44
    ︰
    0.44
     岩
    0.44
     管理
    0.43
    ভালো
    0.43
    Activations Density 0.000%

    No Known Activations