© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100872
    Prev
    Next
    INDEX
    Explanations

    collections of things

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

    comprehensive and scalable user answers

    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
    డ్
    0.51
     année
    0.49
    મેન્ટ
    0.49
    满满
    0.49
    стаў
    0.49
    ણ
    0.49
     પ્રથમ
    0.49
    ຕ
    0.48
     futuras
    0.48
    充满了
    0.48
    POSITIVE LOGITS
     Nucle
    0.44
     inheritance
    0.43
     responder
    0.42
    ve
    0.42
     sä
    0.42
    겁
    0.41
     kü
    0.40
     picker
    0.40
     nitric
    0.40
     conte
    0.40
    Activations Density 0.000%

    No Known Activations