© 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. 22-GEMMASCOPE-RES-131K
    7. 72819
    Prev
    Next
    INDEX
    Explanations

    failed shots and missed attempts

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

    The neuron responds to words describing a forceful “shot” or firing action (e.g. shot, ripped a … shot).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    itemize
    -1.22
    Forrás
    -1.02
    が進
    -1.00
    äldrar
    -0.99
     galinha
    -0.98
    lcccccc
    -0.96
    xrLabel
    -0.96
    readFileSync
    -0.96
    lichten
    -0.95
     régle
    -0.94
    POSITIVE LOGITS
     only
    1.38
     into
    1.09
     siker
    1.04
     just
    1.00
    まち
    0.99
     was
    0.97
     sent
    0.95
    失敗
    0.94
     unsuccessful
    0.93
     실패
    0.93
    Activations Density 0.006%

    No Known Activations