© 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. 137606
    Prev
    Next
    INDEX
    Explanations

    academic citations and foreign words

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

    harmful misuse and discretion

    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
    背
    0.46
     Shelby
    0.45
    仕
    0.45
    奮
    0.44
     chante
    0.44
     gesprek
    0.44
    BackPressed
    0.43
    র্ষি
    0.43
    khart
    0.43
    戰
    0.43
    POSITIVE LOGITS
     сне
    0.52
     ефектив
    0.50
     reú
    0.48
     বিক্র
    0.48
     σύμφωνα
    0.48
     идеально
    0.47
     ตาม
    0.47
     пору
    0.47
     каж
    0.46
    фу
    0.46
    Activations Density 0.000%

    No Known Activations