© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29937
    Prev
    Next
    INDEX
    Explanations

    JSON schema and URLs

    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_31_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
     ist
    0.41
    ("--
    0.37
     Pupp
    0.36
     chống
    0.35
     Asp
    0.35
     denounce
    0.35
    tım
    0.35
     সামাজিক
    0.34
     pupp
    0.34
    čiť
    0.34
    POSITIVE LOGITS
    曼
    0.48
    क्षत्र
    0.43
     प्रतिनिध
    0.42
     Amended
    0.40
    URNS
    0.39
     URI
    0.38
     FileName
    0.37
    ICAN
    0.37
    ⬅
    0.37
    URUK
    0.37
    Activations Density 0.001%

    No Known Activations