© 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. 58018
    Prev
    Next
    INDEX
    Explanations

    increasing positive qualities

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

    The neuron fires on comparative and superlative degree words and intensifying modifiers (e.g. extremely, increasingly, more, efficient) that emphasize improvements or strengths in technical descriptions.

    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
    navigationBar
    -0.83
    vább
    -0.82
    以上の
    -0.81
    TTTT
    -0.81
     país
    -0.81
    Materiál
    -0.80
    伤感
    -0.80
    ╳
    -0.79
     incroyable
    -0.79
     Τ
    -0.78
    POSITIVE LOGITS
     stable
    1.20
     clean
    1.17
     novel
    1.13
     comfortable
    1.13
     firm
    1.12
     lively
    1.06
     durable
    1.06
     relaxed
    1.02
     smooth
    1.02
     accurate
    0.95
    Activations Density 0.025%

    No Known Activations