© 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. 78532
    Prev
    Next
    INDEX
    Explanations

    XML namespaces

    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
     confec
    -0.79
    '~
    -0.78
    OON
    -0.77
     Classi
    -0.77
    CHAN
    -0.77
    kosť
    -0.76
     denke
    -0.76
     ناز
    -0.75
     lisboa
    -0.75
     crosses
    -0.74
    POSITIVE LOGITS
    Masukkan
    0.96
    setTotal
    0.90
    uggles
    0.80
     DOM
    0.78
    itarios
    0.76
    NonQuery
    0.75
    ेज
    0.75
    BarItem
    0.75
    pointer
    0.75
    ๋
    0.75
    Activations Density 0.033%

    No Known Activations