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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12165
    Prev
    Next
    INDEX
    Explanations

    making me, being collected, being disingenuous

    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_16k_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
     yourself
    0.63
    র
    0.59
     daunting
    0.57
    ലെ
    0.56
    д
    0.55
     afore
    0.55
     clicked
    0.54
     unquestion
    0.54
     succinctly
    0.54
     excelled
    0.52
    POSITIVE LOGITS
    ly
    0.64
     сейчас
    0.60
    ails
    0.55
    此时
    0.54
    ting
    0.53
    m
    0.52
     ہیں۔
    0.51
    ta
    0.50
     इन
    0.50
    స్తున్నారు
    0.49
    Activations Density 0.433%

    No Known Activations