© 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. 160741
    Prev
    Next
    INDEX
    Explanations

    shareholders company investors regularly

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

    ADHD

    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
    ｽ
    0.44
    Основные
    0.43
    빕
    0.42
    小组
    0.42
    َس
    0.42
    Initialized
    0.41
    Instructor
    0.41
    गोर
    0.41
    痉
    0.41
    Thankfully
    0.40
    POSITIVE LOGITS
     অন্য
    0.49
     ಇದು
    0.47
     postponing
    0.46
    fue
    0.45
    museum
    0.45
     एखा
    0.45
    ᱸ
    0.44
     Han
    0.44
     courthouse
    0.44
    leftharpoons
    0.44
    Activations Density 0.000%

    No Known Activations