© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21381
    Prev
    Next
    INDEX
    Explanations

    explanation of complex systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Peki
    0.57
    बता
    0.54
     diciembre
    0.51
     Entonces
    0.49
     temporada
    0.48
     jornadas
    0.47
    }=\
    0.46
     enmity
    0.46
     dinero
    0.45
     Tako
    0.45
    POSITIVE LOGITS
     设备
    0.46
     系统
    0.44
     시스템
    0.42
     속에
    0.41
    钕
    0.40
     클릭
    0.39
     활
    0.39
     позволяет
    0.39
     thermost
    0.39
     화면
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.