© 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. 34-GEMMASCOPE-RES-131K
    7. 48790
    Prev
    Next
    INDEX
    Explanations

    power of

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

    The neuron fires on occurrences of the phrase “power of” (especially in “the power of X,” such as “the power of prayer”).

    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
    balancing
    -0.89
    urar
    -0.88
    战
    -0.87
    Drop
    -0.85
     lumières
    -0.84
     PERFECT
    -0.84
    
    -0.83
     côtes
    -0.82
     Klu
    -0.82
    apha
    -0.82
    POSITIVE LOGITS
     suggestion
    1.27
     positive
    1.06
     one
    0.98
     imagination
    0.96
     words
    0.95
     of
    0.90
     using
    0.90
    jaard
    0.89
     people
    0.88
     positiva
    0.86
    Activations Density 0.017%

    No Known Activations