© 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. 92721
    Prev
    Next
    INDEX
    Explanations

    economic stimulus and recovery bills

    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
    ﾕ
    -0.91
     Sank
    -0.79
    roxene
    -0.78
    nię
    -0.77
    zeß
    -0.77
    ⎤
    -0.77
     AllMusic
    -0.77
     التف
    -0.76
    台
    -0.76
    Ừ
    -0.75
    POSITIVE LOGITS
     stimulus
    3.17
     Stimulus
    2.67
    stimulus
    2.63
    Stim
    2.36
     Recovery
    2.02
     stimuli
    1.98
     stimulate
    1.92
    stim
    1.88
     stimul
    1.81
    刺激
    1.78
    Activations Density 0.042%

    No Known Activations