© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 14446
    Prev
    Next
    INDEX
    Explanations

    Irvine and San Diego

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    R
    0.78
    RNB
    0.69
    H
    0.68
    考えると
    0.65
     because
    0.64
    ]',
    0.64
     for
    0.64
    '],
    0.62
    ]",
    0.62
     },
    0.62
    POSITIVE LOGITS
    ל
    0.95
    то
    0.92
    ı
    0.86
    ad
    0.83
    ность
    0.81
    ной
    0.79
    м
    0.78
    ת
    0.77
    тою
    0.75
    ா
    0.74
    Activations Density 0.000%

    No Known Activations