© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 209715
    Prev
    Next
    INDEX
    Explanations

    prides itself

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

    import, could, prices, as, say, father

    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
    觀
    0.49
     imó
    0.42
    ர்
    0.42
    usus
    0.42
    财富
    0.41
    ळ
    0.41
     Realtors
    0.41
     זמן
    0.41
     utility
    0.40
    ა
    0.40
    POSITIVE LOGITS
    np
    0.49
     :\
    0.45
    meat
    0.45
     np
    0.44
     respectivos
    0.44
    듄
    0.44
    sequences
    0.44
     각각
    0.43
    wenden
    0.43
    ceu
    0.43
    Activations Density 0.001%

    No Known Activations