© 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. 39055
    Prev
    Next
    INDEX
    Explanations

    phone numbers with '7'

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

    medical, computer, or sports physics concepts

    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
     स्टेटमेंट
    0.43
     ~~
    0.42
    教练
    0.41
    🦀
    0.41
     coaches
    0.41
     понимаю
    0.41
    觉得自己
    0.40
    क्षात्कार
    0.40
     leto
    0.40
    鸡蛋
    0.39
    POSITIVE LOGITS
    ໄ
    0.46
     மருத்துவ
    0.45
    medical
    0.43
    Medical
    0.42
    Female
    0.42
    Hug
    0.42
    Computer
    0.42
     belieb
    0.42
    Plaintiff
    0.41
     Serviços
    0.41
    Activations Density 0.000%

    No Known Activations