Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1691
    Prev
    Next
    INDEX
    Explanations

    codeterminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     exploratory
    0.74
     মুক্তিবাহিনী
    0.71
     दिर
    0.69
    रुख
    0.67
     एकूण
    0.66
     रोजिक
    0.65
    톄
    0.65
    രുദ്ധ
    0.65
     கீழ
    0.65
     মুক্তিবাহিনীর
    0.64
    POSITIVE LOGITS
    ↵
    0.81
     }
    0.70
    uy
    0.69
     والع
    0.66
    )}
    0.65
     />}
    0.62
     lot
    0.62
     lò
    0.61
    }
    0.60
    怎
    0.60
    Activations Density 0.489%

    No Known Activations