© 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. 64311
    Prev
    Next
    INDEX
    Explanations

    bullet journaling, bullet points, bulletproof

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

    This neuron activates on occurrences of the substring “bullet” (in words like “bullet,” “bulletproof,” “bulletins,” etc.).

    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
     egna
    -0.78
    f
    -0.77
    na
    -0.76
     národ
    -0.75
     المعيار
    -0.75
    Jeremy
    -0.74
     deney
    -0.74
    DK
    -0.73
    "\
    -0.73
     ileti
    -0.72
    POSITIVE LOGITS
    proof
    1.82
     Bullet
    1.57
     bullet
    1.52
    bullet
    1.43
    proofing
    1.40
    PROOF
    1.32
    Bullet
    1.28
     fired
    1.12
     Bullets
    1.09
     proof
    1.04
    Activations Density 0.009%

    No Known Activations