© 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. 185898
    Prev
    Next
    INDEX
    Explanations

    formal agreements and sensitive topics

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

    paragraph about, explore potential

    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
    ا۔
    0.52
    았습니다
    0.51
    勐
    0.49
    았다
    0.49
    sorting
    0.48
    았
    0.48
    ায়
    0.48
    Phir
    0.47
    ⃖
    0.47
    았던
    0.47
    POSITIVE LOGITS
     prostitution
    0.57
     disarmament
    0.57
     unions
    0.56
     designation
    0.54
     treaty
    0.51
     rings
    0.50
     union
    0.47
     manipulated
    0.47
     corruption
    0.47
     weddings
    0.47
    Activations Density 0.000%

    No Known Activations