© 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. 122247
    Prev
    Next
    INDEX
    Explanations

    multilingual indicators

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

    parameters or positional descriptions

    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
     Galer
    0.43
     vez
    0.40
    v
    0.40
    bac
    0.39
     vib
    0.39
     Oz
    0.39
    ことになる
    0.39
    Ê
    0.39
     always
    0.38
    一层
    0.38
    POSITIVE LOGITS
    μα
    0.62
    嫵
    0.54
    ਟੀ
    0.52
     ਦਵਾਈ
    0.52
    錒
    0.52
     учреждения
    0.50
    ująca
    0.50
     ಅಪ
    0.49
    чнай
    0.49
    আন্তর্জাতিক
    0.48
    Activations Density 0.002%

    No Known Activations