© 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. 33494
    Prev
    Next
    INDEX
    Explanations

    place or thing followed by verb

    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
    ！！！”
    -0.96
     returnValue
    -0.92
    ときは
    -0.92
     Terrasse
    -0.90
     }],
    -0.90
     expresó
    -0.88
     />';
    -0.88
    Минусы
    -0.88
    推荐阅读
    -0.87
    轰隆隆
    -0.85
    POSITIVE LOGITS
    はその
    1.50
     would
    1.26
     however
    1.20
     therefore
    1.14
    それを
    1.13
     taką
    1.13
     zrobić
    1.11
     help
    1.06
     will
    1.04
    却
    1.03
    Activations Density 0.073%

    No Known Activations