© 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. 223928
    Prev
    Next
    INDEX
    Explanations

    currency exchange or control

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

    your/yourself/towel/python/mama

    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
    ب
    0.54
    坨
    0.48
     fonction
    0.46
    ब
    0.46
     and
    0.45
    いま
    0.44
     Bede
    0.44
    सा
    0.44
    ㄌ
    0.43
    รี
    0.43
    POSITIVE LOGITS
     času
    0.54
    ILIO
    0.48
    uclear
    0.44
    łącznie
    0.44
    lyan
    0.44
    قاء
    0.43
    IKV
    0.43
     तेज़
    0.43
     ಔಷಧ
    0.42
    لیکن
    0.42
    Activations Density 0.001%

    No Known Activations