© 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. 22-GEMMASCOPE-RES-131K
    7. 66054
    Prev
    Next
    INDEX
    Explanations

    associated press, specific dates

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

    The neuron strongly activates on uppercase names and abbreviations (proper‐noun and agency acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -0.94
    D
    -0.86
    parseInt
    -0.83
    jenigen
    -0.82
    For
    -0.81
    findOne
    -0.79
     Sitzung
    -0.79
    *}
    -0.77
    CascadeType
    -0.77
     عنه
    -0.77
    POSITIVE LOGITS
     his
    1.09
     услу
    0.97
     его
    0.96
     naudo
    0.95
    pośred
    0.94
    𝕘
    0.94
    showed
    0.93
    goti
    0.93
    vetor
    0.93
    Tracce
    0.93
    Activations Density 0.002%

    No Known Activations