© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81373
    Prev
    Next
    INDEX
    Explanations

    peak or point

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

    The neuron fires on words marking extreme points or superlatives—terms like “height,” “peak,” “pinnacle,” or “record” indicating the maximum or high‐point of something.

    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
     increasingly
    -0.93
     постоянно
    -0.88
    AutoresizingMask
    -0.87
    letoe
    -0.85
     rising
    -0.84
     alcune
    -0.84
    tamento
    -0.82
    nitus
    -0.81
     initializer
    -0.81
     ergibt
    -0.79
    POSITIVE LOGITS
    Reached
    1.38
    reached
    1.22
     reached
    1.22
     of
    1.20
     popularity
    1.16
     moment
    1.06
     intensity
    1.02
     moments
    1.01
    moment
    0.98
    瞬間
    0.98
    Activations Density 0.025%

    No Known Activations