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. 100
    Prev
    Next
    INDEX
    Explanations

    self taught

    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
    uglify
    -0.77
    bär
    -0.76
    znam
    -0.75
     pleaf
    -0.73
    avenue
    -0.70
    又不是
    -0.70
    Kedves
    -0.69
    mability
    -0.69
     cowardice
    -0.69
     interesan
    -0.68
    POSITIVE LOGITS
     self
    4.03
    self
    2.69
     Self
    2.45
     taught
    2.41
     самоу
    2.39
    Self
    2.30
     само
    2.14
    SELF
    2.13
     SELF
    2.11
    taught
    2.09
    Activations Density 0.054%

    No Known Activations