© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64499
    Prev
    Next
    INDEX
    Explanations

    Never Say Die

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

    The neuron fires on directive or instruction words—i.e. verbs and adverbs used in giving commands, advice, or strong recommendations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     autophagy
    -0.80
    错了
    -0.79
     chariot
    -0.78
    ጀ
    -0.78
    いよいよ
    -0.78
    medades
    -0.75
     ход
    -0.73
    roppo
    -0.70
    眈
    -0.69
     пару
    -0.69
    POSITIVE LOGITS
    whenever
    0.82
     Nunca
    0.81
     anzub
    0.79
    difficulty
    0.77
     Never
    0.77
    📀
    0.77
     ASS
    0.76
    ￠
    0.75
     ass
    0.75
    äv
    0.74
    Activations Density 0.050%

    No Known Activations