© 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. 63879
    Prev
    Next
    INDEX
    Explanations

    across the

    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
         
    -1.04
     between
    -1.03
     up
    -0.99
     を
    -0.99
     and
    -0.98
     among
    -0.98
     o
    -0.97
            
    -0.94
    etsch
    -0.93
    とも
    -0.92
    POSITIVE LOGITS
     the
    1.55
    鼉
    1.37
     całej
    1.37
     disciplines
    1.36
    across
    1.31
     fraî
    1.30
     multiple
    1.29
     bienvenue
    1.29
     genres
    1.27
     diverses
    1.27
    Activations Density 0.026%

    No Known Activations