© 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. 225830
    Prev
    Next
    INDEX
    Explanations

    each tailored

    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
    तर
    0.46
     दिक्
    0.44
    要素
    0.40
    하기도
    0.39
    感慨
    0.38
    ，“
    0.38
    ましたが
    0.38
    🤏
    0.38
     “‘
    0.37
    橡胶
    0.37
    POSITIVE LOGITS
     каждом
    0.59
     EVERY
    0.57
     każdego
    0.57
     EACH
    0.55
     প্রত্যেক
    0.52
     varje
    0.52
     created
    0.50
     कोणत्याही
    0.49
     každý
    0.49
     setiap
    0.49
    Activations Density 0.002%

    No Known Activations