© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118679
    Prev
    Next
    INDEX
    Explanations

    click on link

    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
     kinda
    -0.84
    avaient
    -0.83
    Section
    -0.82
     gewisser
    -0.81
    those
    -0.80
     ation
    -0.78
    Ux
    -0.77
     momentous
    -0.77
     برخی
    -0.76
     锁
    -0.76
    POSITIVE LOGITS
     link
    2.08
     this
    1.44
     following
    1.42
     ссылке
    1.39
    链接
    1.34
     hyperlink
    1.27
    link
    1.25
     links
    1.19
     url
    1.18
    LINK
    1.16
    Activations Density 0.037%

    No Known Activations