© 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. 30810
    Prev
    Next
    INDEX
    Explanations

    portal URLs

    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
    liert
    -0.76
    pery
    -0.75
    insatz
    -0.75
    ximation
    -0.74
    πάρχ
    -0.72
     تمت
    -0.72
    sschutz
    -0.72
     tags
    -0.70
     reco
    -0.69
    зме
    -0.69
    POSITIVE LOGITS
     portal
    4.97
     Portal
    3.89
     portals
    3.86
    portal
    3.63
    Portal
    3.50
     порта
    2.69
     portail
    2.28
    Портал
    1.90
     PORT
    1.86
     Portail
    1.76
    Activations Density 0.045%

    No Known Activations