© 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. 48719
    Prev
    Next
    INDEX
    Explanations

    railway systems infrastructure

    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
     mobile
    -0.71
    คาร
    -0.69
     celebrado
    -0.68
     onlyOwner
    -0.67
    了一声
    -0.67
    werty
    -0.66
     striking
    -0.65
    rca
    -0.65
    abriel
    -0.65
    xce
    -0.64
    POSITIVE LOGITS
    Kie
    0.92
     infe
    0.91
     Staffel
    0.81
     Camry
    0.79
    Poster
    0.79
    zeniami
    0.79
     Kiefer
    0.79
     Reck
    0.78
    APPLICATION
    0.77
     Suburban
    0.77
    Activations Density 0.022%

    No Known Activations