© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6969
    Prev
    Next
    INDEX
    Explanations

    no choice but

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

    This neuron highlights words and phrases expressing choices or options (e.g., “choice,” “no choice,” “option”).

    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
    甞
    -1.59
    鱟
    -1.55
    禤
    -1.49
     geist
    -1.45
     wholly
    -1.42
    诸多
    -1.40
    鋮
    -1.40
    鈸
    -1.39
     简约
    -1.38
     говорил
    -1.38
    POSITIVE LOGITS
    2
    1.99
    else
    1.99
    }
    1.81
    ).
    1.65
     else
    1.58
    他の
    1.52
    5
    1.52
    ви
    1.48
     необходимые
    1.45
     okre
    1.45
    Activations Density 0.009%

    No Known Activations