© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 326
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    om
    0.81
    i
    0.78
    ﻟ
    0.75
    ่
    0.70
    рных
    0.69
    sg
    0.69
     jornadas
    0.69
    så
    0.68
    ayın
    0.67
    ەکانی
    0.67
    POSITIVE LOGITS
    Пред
    0.91
     militari
    0.90
     uit
    0.89
     軍
    0.88
    Дру
    0.84
    橘
    0.84
     Acest
    0.83
     endet
    0.83
    Dieser
    0.81
     Amnesty
    0.81
    Activations Density 0.001%

    No Known Activations