© 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. 175836
    Prev
    Next
    INDEX
    Explanations

    foreign or possibility words

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

    longer study stretch

    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
    
    0.48
    یدہ
    0.44
    ће
    0.43
     Heimat
    0.42
    ギフト
    0.41
     Amaya
    0.41
    Ninja
    0.41
    ﮢ
    0.41
    Offline
    0.40
     Lagi
    0.40
    POSITIVE LOGITS
    éal
    0.49
     spectre
    0.45
     eğer
    0.45
     quizás
    0.44
     perhaps
    0.44
     pourrait
    0.44
    おそらく
    0.43
    autical
    0.43
    ש
    0.43
     podría
    0.43
    Activations Density 0.000%

    No Known Activations