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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3352
    Prev
    Next
    INDEX
    Explanations

    Just then, justification, mercy

    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_22_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
    cun
    0.79
    ⚠
    0.75
    탬
    0.71
    𝕊
    0.70
    殃
    0.70
    Unit
    0.70
     Wi
    0.69
     wir
    0.68
     bothers
    0.67
     Wir
    0.66
    POSITIVE LOGITS
    ification
    0.94
     articulation
    0.86
     इत्यादि
    0.86
    筈
    0.83
    まさに
    0.83
     derecho
    0.82
    這是
    0.81
     Exactly
    0.79
     такі
    0.79
    ificación
    0.79
    Activations Density 0.013%

    No Known Activations