© 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. 29099
    Prev
    Next
    INDEX
    Explanations

    system standards, first of all, born and raised, .java

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

    sentence endings and punctuation

    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
     aka
    0.46
     надеюсь
    0.45
    usega
    0.44
     vagy
    0.43
     imate
    0.42
    ឬ
    0.41
     rebellious
    0.41
     arba
    0.41
    eseen
    0.41
     restlessness
    0.41
    POSITIVE LOGITS
    子
    0.50
     অ্যাপ
    0.46
    Executor
    0.44
    decorators
    0.44
    实例化
    0.44
    应用
    0.44
     방식으로
    0.43
    类
    0.43
    定制
    0.43
     méthodes
    0.42
    Activations Density 0.000%

    No Known Activations