© 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. 111642
    Prev
    Next
    INDEX
    Explanations

    Developer activity or optional fields

    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
    让人
    0.50
    厂
    0.49
    ır
    0.49
    費
    0.49
    英
    0.48
    イング
    0.48
    挀
    0.48
    𝘦
    0.47
    uomo
    0.47
    messer
    0.47
    POSITIVE LOGITS
     or
    0.55
     supr
    0.50
     Theorem
    0.49
     values
    0.48
     infinite
    0.48
     ionic
    0.48
     Strategy
    0.46
     Ayurveda
    0.46
    !")
    0.46
     SGD
    0.46
    Activations Density 0.011%

    No Known Activations