© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102006
    Prev
    Next
    INDEX
    Explanations

    package identifier

    np_acts-logits-general · gemini-2.5-flash-lite

    the keyword "package" or "namespace" declarations in source code files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     then
    -1.70
    </b>
    -1.59
     some
    -1.58
    </strong>
    -1.50
     daarmee
    -1.48
     it
    -1.47
    </em>
    -1.46
     intends
    -1.41
     things
    -1.33
    </i>
    -1.32
    POSITIVE LOGITS
    🕗
    1.35
     varje
    1.28
    ttes
    1.25
    Sqft
    1.23
    tation
    1.15
     primeira
    1.14
    wną
    1.13
    앓
    1.10
     pertama
    1.09
     appelé
    1.09
    Activations Density 0.054%

    No Known Activations