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. 8013
    Prev
    Next
    INDEX
    Explanations

    setter methods

    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
    在你
    -1.26
     subjug
    -1.22
     Hasta
    -1.14
    狨
    -1.14
    一點
    -1.13
     黑白
    -1.13
    出场
    -1.12
    now
    -1.11
    和你
    -1.10
     抠
    -1.09
    POSITIVE LOGITS
     as
    1.52
    }$.
    1.35
     aside
    1.13
     new
    1.12
     This
    1.10
     and
    1.09
     additional
    1.09
     appropriate
    1.05
     such
    1.04
     Because
    1.02
    Activations Density 0.013%

    No Known Activations