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. 8452
    Prev
    Next
    INDEX
    Explanations

    foreign language 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
     with
    -1.40
     within
    -1.17
     from
    -1.16
     for
    -1.01
     whose
    -0.99
     to
    -0.97
     that
    -0.96
     by
    -0.96
    With
    -0.93
     into
    -0.87
    POSITIVE LOGITS
     décider
    0.95
     contribuer
    0.86
     hivyo
    0.85
     couverts
    0.84
     poca
    0.82
     résister
    0.81
    LITERAL
    0.81
     wis
    0.81
     distrik
    0.81
    ablemente
    0.80
    Activations Density 0.006%

    No Known Activations