© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85367
    Prev
    Next
    INDEX
    Explanations

    releasing or removing

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

    The neuron detects occurrences of the word “out,” especially when used as part of release-oriented phrasal verbs like “put out” (e.g., releasing an album, report, or plug-in).

    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
    be
    -2.44
    C
    -2.28
    of
    -2.28
     they
    -2.19
    Y
    -2.13
    where
    -1.93
    D
    -1.91
    .
    -1.91
    V
    -1.88
    which
    -1.88
    POSITIVE LOGITS
     özellikle
    2.56
    ,”
    2.08
    GEBRA
    1.98
     "
    1.93
    '
    1.86
     ayrıca
    1.84
     a
    1.82
    ',
    1.78
    ໊
    1.73
    
    1.73
    Activations Density 0.004%

    No Known Activations