© 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. 188820
    Prev
    Next
    INDEX
    Explanations

    website, services, operations

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

    highlight differences

    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
     Rodriguez
    0.52
     Th
    0.51
     d
    0.48
     Cahill
    0.48
     Nolan
    0.47
     du
    0.47
     Ha
    0.46
     Ja
    0.46
    rek
    0.46
     Oh
    0.46
    POSITIVE LOGITS
     Fonbet
    0.55
     кабинет
    0.52
    asını
    0.49
    ДИ
    0.48
    ቖ
    0.47
    чными
    0.47
     культура
    0.47
    alarını
    0.46
     раство
    0.46
     подели
    0.46
    Activations Density 0.001%

    No Known Activations