© 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. 97115
    Prev
    Next
    INDEX
    Explanations

    foreign company names and abbreviations

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

    when the

    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
    *'
    0.50
    *;
    0.48
    จริง
    0.47
     красиво
    0.46
    联
    0.45
    精准
    0.45
    两
    0.43
    owano
    0.42
    罹
    0.42
    情形
    0.42
    POSITIVE LOGITS
     anaer
    0.58
     hydrates
    0.52
     Eesti
    0.51
     pemain
    0.50
    NaClO
    0.50
     anaerobic
    0.49
     नेपाली
    0.49
     halides
    0.49
     vegans
    0.48
     hrvats
    0.47
    Activations Density 0.001%

    No Known Activations