© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66350
    Prev
    Next
    INDEX
    Explanations

    along the length or center

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

    The neuron activates on words that indicate spatial direction or orientation (e.g. along, down, center, middle, runs).

    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
     circular
    -1.00
     cross
    -0.99
    circular
    -0.96
    Corners
    -0.91
     Circular
    -0.85
     quadr
    -0.84
     CROSS
    -0.83
     vòng
    -0.83
    circle
    -0.83
     Cross
    -0.83
    POSITIVE LOGITS
     вдоль
    1.81
     along
    1.22
     lungo
    1.21
     spine
    1.20
     longitudinal
    1.15
     length
    1.06
     lengthwise
    1.05
    length
    1.03
     entlang
    1.03
     entire
    0.99
    Activations Density 0.075%

    No Known Activations