© 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. 57780
    Prev
    Next
    INDEX
    Explanations

    US Senator or Congressman

    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
    Not in Any Lists

    No Comments

    Negative Logits
     vård
    -0.80
     Rand
    -0.71
    setNum
    -0.71
    Otros
    -0.69
     single
    -0.69
    bord
    -0.68
    kranz
    -0.68
     californ
    -0.66
     Mot
    -0.66
    bür
    -0.65
    POSITIVE LOGITS
     bipartisan
    1.05
     Appropri
    0.80
     biodiesel
    0.77
     appropri
    0.76
     Cramer
    0.74
    ázky
    0.72
     castor
    0.72
    Aca
    0.72
     リゾート
    0.72
     amyloid
    0.71
    Activations Density 0.055%

    No Known Activations