© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91993
    Prev
    Next
    INDEX
    Explanations

    battle of names

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

    The neuron strongly activates on occurrences of the phrase “Battle of,” effectively flagging named battles.

    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
    agenda
    -0.81
    ErrorType
    -0.78
     tangerang
    -0.75
    lijah
    -0.75
    фициальный
    -0.74
     Announcements
    -0.74
     announcements
    -0.73
    lucy
    -0.72
    jason
    -0.71
    puma
    -0.69
    POSITIVE LOGITS
     Battle
    2.36
     battle
    2.19
    Battle
    2.14
    battle
    2.05
     battles
    1.86
     BATTLE
    1.60
     battaglia
    1.53
     batalla
    1.52
    BATTLE
    1.51
     Schlacht
    1.48
    Activations Density 0.032%

    No Known Activations