© 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. 150684
    Prev
    Next
    INDEX
    Explanations

    legal structures or definitions

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

    capturing variables

    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
    龛
    0.46
     полной
    0.44
    gleichen
    0.42
    ászló
    0.42
     vivo
    0.41
    ാര്യ
    0.41
    师
    0.40
     Шта
    0.40
     Сай
    0.40
    睡
    0.40
    POSITIVE LOGITS
    eserc
    0.47
    رل
    0.47
    นน
    0.46
    ử
    0.45
    含ま
    0.45
     certains
    0.44
    ковые
    0.44
    ื่ม
    0.44
     }+\
    0.43
     entendu
    0.42
    Activations Density 0.003%

    No Known Activations