© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101057
    Prev
    Next
    INDEX
    Explanations

    AI audience requests

    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_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
    )
    0.47
     activates
    0.46
     decyz
    0.41
     άλλ
    0.41
      
    0.41
     Zone
    0.39
     walkable
    0.39
    弊
    0.39
     этот
    0.38
    のお店
    0.38
    POSITIVE LOGITS
    㥆
    0.52
    intestin
    0.50
     personnages
    0.50
    णातील
    0.49
    તિહાસ
    0.48
    zechoslovakia
    0.48
     வரலாற்று
    0.48
    assem
    0.47
     inspir
    0.47
     ਅਤੇ
    0.47
    Activations Density 0.015%

    No Known Activations