© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129818
    Prev
    Next
    INDEX
    Explanations

    loop counter `i`

    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
    avaient
    -0.83
    genus
    -0.77
     herida
    -0.76
     Verizon
    -0.75
     दिन
    -0.74
    logies
    -0.73
     Compiled
    -0.73
     boneless
    -0.72
    mutant
    -0.72
     além
    -0.72
    POSITIVE LOGITS
    Then
    1.01
     médio
    1.00
     aboli
    0.90
     fofo
    0.89
     feminino
    0.88
     espet
    0.88
     Auflösung
    0.84
    Any
    0.84
     Herkunft
    0.84
    otriva
    0.83
    Activations Density 0.016%

    No Known Activations