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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 26103
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    273,612 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ज़
    0.42
     hypothetical
    0.38
    ّ
    0.33
    ASC
    0.33
    न्ड
    0.32
    IGet
    0.31
     siphon
    0.31
    }:
    0.31
     تو
    0.30
    mentioned
    0.30
    POSITIVE LOGITS
     Oui
    0.39
     Ответ
    0.38
    <unused598>
    0.38
     {@
    0.36
    ctree
    0.36
    affaires
    0.36
    દેશ
    0.35
    ucie
    0.35
    㕲
    0.35
    castellan
    0.35
    Activations Density 0.007%

    No Known Activations