© 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. 47755
    Prev
    Next
    INDEX
    Explanations

    code includes

    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
     for
    -2.20
     depending
    -1.29
     enligt
    -1.26
     según
    -1.25
     according
    -1.15
    根据
    -1.04
     selon
    -1.03
     Depending
    -1.02
     według
    -0.98
     согласно
    -0.96
    POSITIVE LOGITS
     بينما
    1.03
    sao
    0.95
     Cuar
    0.85
     ninguna
    0.85
    while
    0.83
    should
    0.82
    齑
    0.82
    !
    0.82
    €)
    0.81
    ppure
    0.81
    Activations Density 0.001%

    No Known Activations