© 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. 33512
    Prev
    Next
    INDEX
    Explanations

    and brain, web, terms, addressed

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

    how things work

    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
     Ow
    0.46
     rooftops
    0.44
     campos
    0.44
     வகையான
    0.43
    wanted
    0.43
    spanning
    0.43
    鴉
    0.43
     ámbitos
    0.42
    lighting
    0.40
     Towards
    0.40
    POSITIVE LOGITS
    手术
    0.49
    ılıyor
    0.47
     인터넷
    0.47
     медицин
    0.46
    手術
    0.45
    MEDICAL
    0.45
    reszt
    0.45
     fortunately
    0.44
    会儿
    0.44
    瘪
    0.44
    Activations Density 0.000%

    No Known Activations