© 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. 27555
    Prev
    Next
    INDEX
    Explanations

    locations and dates

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

    article beginnings

    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
    活力
    0.40
    agena
    0.40
    信任
    0.40
    edLeft
    0.40
     మహ
    0.39
    书籍
    0.38
     माण
    0.38
    淇
    0.38
     చేరు
    0.38
     fiducia
    0.37
    POSITIVE LOGITS
     ඔහු
    0.43
     ඔහුගේ
    0.43
    Low
    0.41
     alternately
    0.40
     redund
    0.39
    झाने
    0.39
     behe
    0.39
     Spawn
    0.38
    ('${
    0.38
     his
    0.38
    Activations Density 0.001%

    No Known Activations