© 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. 3192
    Prev
    Next
    INDEX
    Explanations

    states and cities

    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
     bicicletas
    -1.16
    閬
    -1.14
    ときに
    -1.14
    我们会
    -1.13
    きょう
    -1.08
     ПРИ
    -1.07
    沨
    -1.07
     .
    -1.07
     ſet
    -1.07
     asume
    -1.06
    POSITIVE LOGITS
     has
    2.47
     is
    2.42
     had
    1.82
     isn
    1.65
    ’
    1.61
     residents
    1.47
     currently
    1.45
     have
    1.42
     became
    1.40
     was
    1.38
    Activations Density 0.128%

    No Known Activations