© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79512
    Prev
    Next
    INDEX
    Explanations

    charging into battle

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    zése
    -0.80
    riol
    -0.77
    MeasureSpec
    -0.75
    licit
    -0.75
    uminous
    -0.75
     criada
    -0.74
    Php
    -0.74
    archical
    -0.74
    odyne
    -0.73
    ुट
    -0.72
    POSITIVE LOGITS
     charge
    4.06
     charging
    3.97
    charge
    3.36
    Charge
    3.34
     charges
    3.28
    Charging
    3.25
     Charging
    3.19
     Charge
    3.19
     charged
    3.16
    charging
    3.09
    Activations Density 0.028%

    No Known Activations