© 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. 15081
    Prev
    Next
    INDEX
    Explanations

    definable, saturated fields

    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
     alkoh
    -1.52
    🤎
    -1.41
     kommunik
    -1.39
     basili
    -1.37
    kamera
    -1.35
     kommun
    -1.35
    
    -1.31
    шники
    -1.27
     mereka
    -1.26
     ideen
    -1.26
    POSITIVE LOGITS
     зараз
    1.23
     things
    1.18
    匾
    1.18
     zamiast
    1.18
     الحكومة
    1.18
     використо
    1.17
     kinds
    1.17
     conductas
    1.16
    就可以了
    1.16
     wobec
    1.14
    Activations Density 0.018%

    No Known Activations