© 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. 57958
    Prev
    Next
    INDEX
    Explanations

    Power Rangers

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

    This neuron strongly responds to the Roman-letter components of the Japanese Tokusatsu team name “Uchu Sentai Kyuranger.”

    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
    下手
    -0.76
    carto
    -0.72
     considers
    -0.69
     lactic
    -0.69
    mittance
    -0.67
     aerolí
    -0.66
    жкой
    -0.65
    мум
    -0.64
    мента
    -0.64
    HIDE
    -0.64
    POSITIVE LOGITS
     ranger
    1.55
     rangers
    1.50
     Rangers
    1.49
     Ranger
    1.47
    Ranger
    1.33
    Rangers
    1.30
     Power
    1.23
    ranger
    1.16
    Power
    1.03
     Rita
    0.99
    Activations Density 0.010%

    No Known Activations