© 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. 58176
    Prev
    Next
    INDEX
    Explanations

    LCD Enable, INT Declaration

    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
     estratégico
    -0.81
    зани
    -0.77
    animaux
    -0.76
     strategia
    -0.76
    كو
    -0.75
    lccccc
    -0.75
     insulator
    -0.75
     プラ
    -0.75
    espacio
    -0.75
     preocupado
    -0.75
    POSITIVE LOGITS
     Enable
    1.58
     enable
    1.41
    Enable
    1.32
    enable
    1.31
    ENABLE
    1.03
     enabling
    0.98
     pins
    0.94
     Enables
    0.93
     trigger
    0.91
     ENABLE
    0.89
    Activations Density 0.036%

    No Known Activations