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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16597
    Prev
    Next
    INDEX
    Explanations

    come to the right place

    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
    ü
    0.42
     உங்களுக்கு
    0.38
     niñas
    0.38
    বাঙ্গ
    0.37
    HEALTH
    0.37
     तुम्हाला
    0.37
     saludables
    0.37
    夏季
    0.36
    ご紹介
    0.36
    allaitement
    0.36
    POSITIVE LOGITS
     اكيد
    0.42
     є
    0.40
     мати
    0.40
     છું
    0.39
     Soul
    0.38
     reversal
    0.38
     decisive
    0.37
    irnov
    0.36
    γγ
    0.36
    coder
    0.36
    Activations Density 0.002%

    No Known Activations