© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4098
    Prev
    Next
    INDEX
    Explanations

    code snippets and data headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    ']]
    0.70
    è
    0.69
    )]:
    0.68
     компью
    0.67
     lawyers
    0.67
     toán
    0.67
    ходи
    0.66
    电脑
    0.65
    ]]:
    0.65
    )]
    0.64
    POSITIVE LOGITS
     Tonight
    0.72
     Tomorrow
    0.71
     her
    0.69
    সুর
    0.69
    娜
    0.68
     tomorrow
    0.66
     Regarding
    0.66
     storyline
    0.66
     दोहरा
    0.65
     Seeking
    0.64
    Activations Density 0.074%

    No Known Activations