© 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. 22-GEMMASCOPE-RES-131K
    7. 33689
    Prev
    Next
    INDEX
    Explanations

    year context

    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_22/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
     night
    -1.02
     delincuentes
    -0.94
     akhir
    -0.91
    łem
    -0.88
     inflación
    -0.87
    uu
    -0.86
     dinner
    -0.86
     noche
    -0.85
    एन
    -0.85
    啸
    -0.84
    POSITIVE LOGITS
     morning
    1.26
     MORNING
    1.02
     temprano
    0.98
    早
    0.96
     Morning
    0.94
    morning
    0.92
     early
    0.92
     before
    0.90
    Morning
    0.90
    Specifiche
    0.90
    Activations Density 0.070%

    No Known Activations