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. 8409
    Prev
    Next
    INDEX
    Explanations

    events following an action

    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
     that
    -1.66
     any
    -1.27
     has
    -1.26
     will
    -1.23
     might
    -1.23
     had
    -1.20
     all
    -1.16
     such
    -1.13
     would
    -1.12
     have
    -1.08
    POSITIVE LOGITS
     being
    1.93
     deem
    1.39
     becoming
    1.34
     confess
    1.30
    being
    1.23
     orchestr
    1.21
     unsuccessfully
    1.18
     ſte
    1.17
     controversi
    1.16
     étant
    1.16
    Activations Density 0.062%

    No Known Activations