© 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. 24-GEMMASCOPE-2-RES-262K
    7. 8901
    Prev
    Next
    INDEX
    Explanations

    called "role", "file", "model", "column"

    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_24_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
    ለያዩ
    0.49
     menyenangkan
    0.47
    ட்டு
    0.45
    ../
    0.44
     função
    0.44
     แปล
    0.44
    ພາ
    0.43
     কথ
    0.43
    λει
    0.42
     różnych
    0.41
    POSITIVE LOGITS
     called
    0.93
     namely
    0.84
    called
    0.82
     llamado
    0.81
     denominada
    0.81
     denominado
    0.80
     chamado
    0.80
     llamada
    0.78
     M
    0.77
    namely
    0.76
    Activations Density 0.023%

    No Known Activations