© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 247032
    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_31_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
     bantu
    0.49
     toán
    0.48
    АТО
    0.48
     freepik
    0.46
     aerob
    0.46
     multicast
    0.46
    \}-
    0.46
    翛
    0.46
     coolant
    0.45
     Bantu
    0.45
    POSITIVE LOGITS
    imit
    0.47
     July
    0.47
    Human
    0.46
    u
    0.45
    OCK
    0.44
    ung
    0.43
    ie
    0.43
     lâ
    0.43
     점
    0.42
    Article
    0.42
    Activations Density 0.001%

    No Known Activations