© 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. 74085
    Prev
    Next
    INDEX
    Explanations

    sequences following common words

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

    insurance protects

    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
    to
    0.53
    전
    0.49
    telling
    0.44
    tailed
    0.44
    權
    0.44
    t
    0.44
    tail
    0.43
    will
    0.43
    า
    0.42
    隊
    0.42
    POSITIVE LOGITS
     مجموعة
    0.46
     Tucson
    0.43
     biopsy
    0.43
     Adobe
    0.42
     Ferrara
    0.42
     Navajo
    0.42
     transcribe
    0.42
     Reforma
    0.41
     adob
    0.41
    陆续
    0.41
    Activations Density 0.000%

    No Known Activations