© 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. 8038
    Prev
    Next
    INDEX
    Explanations

    students or characters

    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
    ка
    1.85
    하는
    1.78
    ти
    1.75
    와
    1.73
    శ
    1.62
    শ
    1.54
     стать
    1.50
    क
    1.50
    들
    1.50
     จะ
    1.48
    POSITIVE LOGITS
    ের
    2.73
    ों
    2.31
    ات
    2.11
    ો
    2.09
    EARCH
    1.96
    ä
    1.83
    ς
    1.82
    ла
    1.80
    ütt
    1.77
    ysteem
    1.70
    Activations Density 0.129%

    No Known Activations