© 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. 203447
    Prev
    Next
    INDEX
    Explanations

    installed, time, switch

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

    targeted subset

    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
     entusiasmo
    0.43
    热情
    0.40
    篾
    0.39
    ামার
    0.38
     entusi
    0.38
    লাপ
    0.37
     enthusiasm
    0.36
     enthous
    0.36
    πισ
    0.35
     новом
    0.35
    POSITIVE LOGITS
     somit
    0.49
    ۔
    0.48
    に係る
    0.45
     entsprechende
    0.42
     در
    0.41
     angegeben
    0.41
     کە
    0.40
     aswell
    0.39
     trois
    0.39
    depending
    0.39
    Activations Density 0.002%

    No Known Activations