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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 244496
    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
    SCHRAMM
    0.52
    стера
    0.51
    シャン
    0.49
     eyelids
    0.46
    ôm
    0.46
    р
    0.46
    (",")
    0.45
    upon
    0.44
     univerz
    0.44
     toen
    0.44
    POSITIVE LOGITS
     {
    0.49
    class
    0.48
     Moved
    0.46
    tait
    0.45
    t
    0.43
     trait
    0.42
     class
    0.41
     நடத்தி
    0.41
     threat
    0.40
     booked
    0.40
    Activations Density 0.003%

    No Known Activations