© 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. 31281
    Prev
    Next
    INDEX
    Explanations

    to which

    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
     abhängig
    -0.85
    IKA
    -0.83
     нужда
    -0.83
    远离
    -0.80
     Dependent
    -0.80
     Buffered
    -0.79
     Pé
    -0.79
    Ŭ
    -0.78
    himovic
    -0.77
     CAPE
    -0.75
    POSITIVE LOGITS
     owe
    1.02
     belong
    0.98
     belongs
    0.94
     referenties
    0.92
     owes
    0.91
     pertenecen
    0.91
     respond
    0.90
     ascribed
    0.89
     applies
    0.88
     refers
    0.88
    Activations Density 0.025%

    No Known Activations