© 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. 150618
    Prev
    Next
    INDEX
    Explanations

    assumed string definition

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

    foreign languages and places

    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
    ဝ်
    0.41
     состоит
    0.41
    温泉
    0.40
    日期
    0.40
    상은
    0.39
    主机
    0.39
    ὲ
    0.36
    配合
    0.36
     נמצא
    0.36
     солнце
    0.36
    POSITIVE LOGITS
     inoltre
    0.47
     bessere
    0.45
     Amerika
    0.45
     dersimizde
    0.45
    اموش
    0.45
     Alat
    0.43
     Fuerza
    0.43
     Почему
    0.43
     Aussi
    0.43
     Marxism
    0.42
    Activations Density 0.001%

    No Known Activations