© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    shoot or shooting

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

    This neuron fires on tokens that form the main title or heading at the start of a document—e.g. the repeated “Shoot the Moon” title lines.

    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
    cista
    -0.92
    ȧ
    -0.92
     Fossil
    -0.87
    idiv
    -0.85
    mically
    -0.84
    克力
    -0.81
    scaron
    -0.81
     Define
    -0.80
    cli
    -0.80
    radiated
    -0.79
    POSITIVE LOGITS
     shoot
    2.06
     shooting
    1.97
     shoots
    1.76
     Shooting
    1.74
    shoot
    1.74
    Shooting
    1.72
     Shoot
    1.66
    Shoot
    1.62
    shooting
    1.59
     shot
    1.38
    Activations Density 0.015%

    No Known Activations