© 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. 235867
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

    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
    ah
    0.50
    اه
    0.49
    a
    0.47
     编辑
    0.45
     camper
    0.43
    ড়ার
    0.43
     العالم
    0.42
    acjach
    0.41
     الآ
    0.41
    စိတ်အပိုင်း
    0.40
    POSITIVE LOGITS
     మీకు
    0.57
     మీరు
    0.48
     અમારા
    0.48
    きたい
    0.48
     мои
    0.47
    +|
    0.46
    உங்கள்
    0.46
     உங்களுக்கு
    0.46
     તમે
    0.45
    你们
    0.44
    Activations Density 0.001%

    No Known Activations