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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1418
    Prev
    Next
    INDEX
    Explanations

    mathematical problem solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    
    0.53
     احساس
    0.47
    ᖃ
    0.47
     دائ
    0.47
    ການ
    0.46
     glas
    0.45
     종
    0.45
     groovy
    0.45
    olata
    0.44
     XIV
    0.44
    POSITIVE LOGITS
    ់
    0.40
    <unused60>
    0.39
    <0x10>
    0.35
     quizá
    0.35
    ڑھ
    0.34
     trzeba
    0.34
    0
    0.34
    9
    0.33
    albeit
    0.32
     proceeds
    0.32
    Activations Density 1.647%

    No Known Activations