© 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. 48926
    Prev
    Next
    INDEX
    Explanations

    two additional

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

    text after punctuation or common words

    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
    鬨
    0.52
     reconstru
    0.47
    แย
    0.47
    स्ट
    0.47
     BONDS
    0.46
     рей
    0.46
     ABO
    0.46
    ل
    0.45
     partitions
    0.45
     ocasiones
    0.45
    POSITIVE LOGITS
    েক
    0.48
     devotional
    0.46
    aporation
    0.46
     نیز
    0.46
     ሂደት
    0.45
    াস
    0.44
    Appending
    0.44
     দেবতা
    0.44
    Killing
    0.43
     Hearing
    0.43
    Activations Density 0.000%

    No Known Activations