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. 67
    Prev
    Next
    INDEX
    Explanations

    permissions and versions

    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
     siihen
    -0.82
     курс
    -0.81
     jūs
    -0.79
    akyti
    -0.77
    intptr
    -0.75
    otry
    -0.73
    荻
    -0.73
     RN
    -0.71
     know
    -0.69
    大量的
    -0.69
    POSITIVE LOGITS
    PHYSICAL
    0.79
    arache
    0.78
    ాయ
    0.77
    arriver
    0.76
     [{\
    0.75
     decisions
    0.74
    ESSIONAL
    0.74
     Pernambuco
    0.73
    sapato
    0.73
    ところが
    0.72
    Activations Density 0.001%

    No Known Activations