© 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. 107993
    Prev
    Next
    INDEX
    Explanations

    state government agencies

    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
    iphery
    -0.77
     therefrom
    -0.77
     Hvad
    -0.75
     ダイニング
    -0.75
    IFICATIONS
    -0.73
    Volker
    -0.72
     eSports
    -0.72
    లు
    -0.72
    isbol
    -0.71
     sén
    -0.70
    POSITIVE LOGITS
     coastal
    1.14
    Governor
    0.82
     fur
    0.80
    KOH
    0.75
    Christmas
    0.75
    coastal
    0.75
    strijden
    0.75
    Natural
    0.73
     beach
    0.73
     CZ
    0.73
    Activations Density 0.016%

    No Known Activations