© 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. 257618
    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
     sticks
    0.49
    厢
    0.43
    wheeled
    0.42
    ridden
    0.42
    setRoi
    0.42
     โอ้
    0.41
     cylinders
    0.40
     বিস্ফ
    0.40
     fingers
    0.39
     bothers
    0.39
    POSITIVE LOGITS
    警
    0.48
    ändige
    0.48
     velocidade
    0.47
     souvent
    0.47
     impos
    0.47
    ܠܐ
    0.47
    elerin
    0.46
    чення
    0.46
    تها
    0.46
     seinem
    0.46
    Activations Density 0.001%

    No Known Activations