© 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. 206767
    Prev
    Next
    INDEX
    Explanations

    regions and nationalities

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

    LinkedIn posts and team meetings

    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
     ہمیشہ
    0.46
    ặt
    0.45
     बस्ती
    0.45
     टा
    0.43
     پانی
    0.42
     thủ
    0.42
     पाण्याची
    0.41
    肠
    0.41
     새로
    0.41
    fieldname
    0.40
    POSITIVE LOGITS
     canadian
    0.48
     canada
    0.43
     смысле
    0.43
    世界
    0.43
     american
    0.42
     distribute
    0.42
     mexican
    0.41
    Canadian
    0.41
     manufacturing
    0.41
     generate
    0.41
    Activations Density 0.000%

    No Known Activations