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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85929
    Prev
    Next
    INDEX
    Explanations

    package names and types

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

    The neuron spotlights occurrences of the identifier “package” (e.g. in filenames, declarations, or metadata fields) across various programming and config files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    髎
    -2.25
    眎
    -2.20
    毉
    -2.13
     predominantly
    -2.08
     famí
    -2.05
     pezzi
    -2.05
    臯
    -2.03
     decidedly
    -2.00
    屙
    -1.99
     contemplating
    -1.98
    POSITIVE LOGITS
    d
    2.59
     Since
    2.42
    Since
    2.27
    :
    2.20
     Surprisingly
    2.16
     ensure
    2.14
     Several
    2.09
     Both
    2.08
     Combining
    2.06
    </td>
    2.05
    Activations Density 0.019%

    No Known Activations