© 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. 2880
    Prev
    Next
    INDEX
    Explanations

    programming code identifiers

    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
    ebly
    -1.12
     gekocht
    -1.07
     aqueles
    -1.03
     Paramètres
    -1.02
     ingenting
    -1.00
     vorige
    -1.00
     soprattutto
    -1.00
     ACKNOWLEDGMENTS
    -0.98
     angebra
    -0.98
     Incluye
    -0.96
    POSITIVE LOGITS
     my
    2.38
     My
    1.41
    my
    1.38
     MY
    1.30
     first
    1.25
     your
    1.23
     our
    1.20
     meu
    1.17
     meine
    1.09
    My
    1.05
    Activations Density 0.103%

    No Known Activations