© 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. 57319
    Prev
    Next
    INDEX
    Explanations

    landed after pass or cross

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

    This neuron fires on the specific sports‐play phrase describing a goal scored by a “shot that slowly trickled between the goalie’s pads.”

    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
     Shooting
    -0.88
    🖍
    -0.84
    鍏
    -0.84
    ឿ
    -0.81
    държа
    -0.81
     יה
    -0.80
    ínű
    -0.78
    Shooting
    -0.77
     trekken
    -0.77
    োগ
    -0.77
    POSITIVE LOGITS
     bounced
    1.27
     bounces
    1.17
     landed
    1.16
     bounce
    1.13
     lands
    1.05
     destined
    1.05
     caught
    0.99
     deflected
    0.98
     landing
    0.96
     into
    0.95
    Activations Density 0.006%

    No Known Activations