© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111382
    Prev
    Next
    INDEX
    Explanations

    code referencing current directory

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

    the `__DIR__` constant in PHP code, particularly when used for file path operations.

    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
     when
    -1.92
     any
    -1.88
    垕
    -1.76
     lavish
    -1.75
    ၟ
    -1.73
     essencial
    -1.71
    荩
    -1.69
     EVERY
    -1.66
     ALWAYS
    -1.65
     where
    -1.63
    POSITIVE LOGITS
    .
    2.52
    0
    2.23
    3
    2.17
    4
    2.14
    8
    2.02
    </strong>
    2.00
    5
    1.99
     apprehen
    1.84
    7
    1.78
    鹇
    1.72
    Activations Density 0.002%

    No Known Activations