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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8630
    Prev
    Next
    INDEX
    Explanations

    exclamations and interjections

    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
    ent
    -1.02
     FUCKING
    -1.01
    ery
    -0.99
     seit
    -0.98
     FUCK
    -0.97
    呵呵
    -0.97
     COMERC
    -0.97
    ult
    -0.96
    Citiți
    -0.96
     erne
    -0.94
    POSITIVE LOGITS
     or
    2.42
     или
    1.66
    または
    1.59
     wait
    1.53
     Seriously
    1.47
    或者
    1.44
     atleast
    1.41
     kidding
    1.37
    或是
    1.37
    或
    1.36
    Activations Density 0.119%

    No Known Activations