© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115890
    Prev
    Next
    INDEX
    Explanations

    included .h or .hpp files

    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
     bēr
    -1.05
    Qed
    -1.02
     būs
    -0.92
     viņ
    -0.91
    quares
    -0.87
    Nursing
    -0.87
    Daha
    -0.85
    Petsc
    -0.85
    Oby
    -0.85
     رغم
    -0.84
    POSITIVE LOGITS
     DirectX
    1.05
    Xbox
    0.96
     xbox
    0.96
     toilette
    0.94
     Wolverhampton
    0.90
     shader
    0.89
     Radeon
    0.88
     Xbox
    0.88
     manta
    0.88
     trivi
    0.87
    Activations Density 0.104%

    No Known Activations