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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 149
    Prev
    Next
    INDEX
    Explanations

    mathematical functions or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姪
    -0.99
    主婦
    -0.93
    ͌
    -0.92
    ͯ
    -0.92
    基本的
    -0.91
    ͩ
    -0.91
    orz
    -0.91
    蟄
    -0.89
     misunderstand
    -0.88
    もあって
    -0.86
    POSITIVE LOGITS
    に入れる
    0.96
    round
    0.95
     nossa
    0.94
     floor
    0.93
     luxurious
    0.91
     financially
    0.91
    floor
    0.91
     alertDialog
    0.91
    发布
    0.91
    誣
    0.91
    Activations Density 0.002%

    No Known Activations