© 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. 73428
    Prev
    Next
    INDEX
    Explanations

    GDP, GPA, GFP, Awards, Accurate

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

    The neuron selectively activates on three‐letter, all‐caps acronyms (e.g. GDP, GPA, GFP).

    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
    𖤣
    -2.67
    麈
    -2.67
    瑧
    -2.61
     شیپور
    -2.56
    StoryboardSegue
    -2.55
    kabau
    -2.52
    隄
    -2.52
    irmish
    -2.52
    mybatisplus
    -2.52
    jestel
    -2.52
    POSITIVE LOGITS
     
    3.38
    -
    2.94
    s
    2.88
    2
    2.66
    ’
    2.61
    ve
    2.48
    O
    2.45
    R
    2.42
    P
    2.39
    W
    2.39
    Activations Density 0.003%

    No Known Activations