© 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. 118979
    Prev
    Next
    INDEX
    Explanations

    File storage locations

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

    references to external storage paths and directories in Android file operations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects mentions of Android external storage or media/gallery directory paths.

    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
    😊
    -1.43
     Diseño
    -1.38
     voordat
    -1.37
     når
    -1.37
    物の
    -1.37
    .":
    -1.36
     demandent
    -1.35
    鐃
    -1.35
     antigos
    -1.34
     WIL
    -1.34
    POSITIVE LOGITS
    .
    1.58
     begins
    1.44
     as
    1.42
     would
    1.42
     one
    1.42
     noteworthy
    1.41
     get
    1.41
     from
    1.38
     could
    1.35
     Adding
    1.34
    Activations Density 0.034%

    No Known Activations