© 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. 141618
    Prev
    Next
    INDEX
    Explanations

    dog breed

    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
    ک
    1.06
    ী
    1.02
    0
    0.88
    つ
    0.86
    th
    0.84
    }
    0.84
    *
    0.82
    ב
    0.82
    д
    0.81
    tr
    0.80
    POSITIVE LOGITS
    0.81
    การ
    0.80
    ت
    0.77
     Dance
    0.73
    യും
    0.69
     Serb
    0.68
     Canarias
    0.67
     Tiv
    0.66
     Wanderers
    0.66
     Teb
    0.66
    Activations Density 0.000%

    No Known Activations