© 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. 107996
    Prev
    Next
    INDEX
    Explanations

    live in

    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
     هناك
    -0.90
    hilterra
    -0.84
    ċi
    -0.82
    Ŗ
    -0.81
    endida
    -0.80
    \}}
    -0.80
    ForRow
    -0.78
     intracellular
    -0.77
    Initialized
    -0.75
    JON
    -0.75
    POSITIVE LOGITS
     in
    2.72
    in
    1.27
     In
    1.15
     فيه
    1.14
    In
    1.12
     میں
    0.93
    NameIn
    0.90
     în
    0.87
     IN
    0.82
    IsIn
    0.81
    Activations Density 0.024%

    No Known Activations