© 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. 31376
    Prev
    Next
    INDEX
    Explanations

    fighting contexts

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

    The neuron fires on relatively uncommon or content-bearing tokens (i.e. words that are neither frequent function words nor punctuation).

    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
    zzet
    -1.07
    Responsibilities
    -1.01
     urodz
    -0.96
     dát
    -0.96
     explotación
    -0.94
     conductores
    -0.93
    ínica
    -0.92
    written
    -0.91
     marié
    -0.90
     melewati
    -0.89
    POSITIVE LOGITS
     fighting
    1.11
     against
    1.02
     teamed
    1.01
     injured
    0.98
     using
    0.98
     fight
    0.98
     relying
    0.95
    連携
    0.95
    frontal
    0.95
     fought
    0.95
    Activations Density 0.001%

    No Known Activations