© 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. 76696
    Prev
    Next
    INDEX
    Explanations

    ATM Systems

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

    related conjunctions and explanations

    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
    ل
    0.66
    ن
    0.57
    ك
    0.56
    ت
    0.55
    ountains
    0.50
    姓
    0.47
    n
    0.47
    一
    0.47
    ي
    0.46
    ه
    0.45
    POSITIVE LOGITS
     μεταξύ
    0.54
    jä
    0.52
     mengenai
    0.51
    VING
    0.51
     apabila
    0.50
     ἢ
    0.50
     veya
    0.47
    ченной
    0.47
     बिंदु
    0.46
     Concerning
    0.46
    Activations Density 0.001%

    No Known Activations