© 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. 22-GEMMASCOPE-RES-131K
    7. 66119
    Prev
    Next
    INDEX
    Explanations

    policy proposals and debates

    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_22/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
    utan
    -1.13
     میشود
    -1.13
    uran
    -1.13
     foncé
    -1.12
     protože
    -1.02
    ļas
    -1.02
    tismo
    -1.01
    depuis
    -0.99
    stdafx
    -0.97
     Boletín
    -0.96
    POSITIVE LOGITS
     would
    1.91
     proposed
    1.44
     proposal
    1.29
     proposals
    1.20
     idea
    1.20
     bill
    1.10
     Would
    1.06
     wäre
    1.05
     debate
    1.05
     system
    1.02
    Activations Density 0.079%

    No Known Activations