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. 8185
    Prev
    Next
    INDEX
    Explanations

    distributed under the license

    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
    падает
    -0.79
     Rhys
    -0.74
    承受
    -0.69
    invasive
    -0.67
    trak
    -0.67
    ԁ
    -0.66
    nagel
    -0.65
     lucha
    -0.65
    nsan
    -0.65
     Finds
    -0.65
    POSITIVE LOGITS
     Nadine
    0.74
    コー
    0.68
     Ewig
    0.65
     otwar
    0.64
     ос
    0.64
     Isto
    0.63
    aduras
    0.62
    Continued
    0.62
    ولد
    0.61
    JQ
    0.61
    Activations Density 0.077%

    No Known Activations