© 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. 117710
    Prev
    Next
    INDEX
    Explanations

    army contexts

    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
    をします
    -0.91
    にします
    -0.91
     Scary
    -0.90
    を行います
    -0.88
     Schwangerschaft
    -0.86
    ioro
    -0.85
    気がします
    -0.84
    をしています
    -0.83
    Somewhat
    -0.81
     изменя
    -0.81
    POSITIVE LOGITS
    บ
    0.98
     подобрать
    0.92
    ペン
    0.88
    onload
    0.88
    Bean
    0.88
    TAGE
    0.88
    Graphics
    0.86
    &$
    0.86
     REGULATIONS
    0.85
     חיי
    0.85
    Activations Density 0.009%

    No Known Activations