© 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. 38918
    Prev
    Next
    INDEX
    Explanations

    transmediapath

    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
    ICIO
    -1.04
    ="";
    -0.99
     this
    -0.98
     racconta
    -0.96
    )((
    -0.92
     vergangenen
    -0.91
     Tö
    -0.90
    」、「
    -0.90
     it
    -0.89
     höl
    -0.88
    POSITIVE LOGITS
     xinh
    0.96
     ausgeführt
    0.94
     PARAMETER
    0.94
     gebunden
    0.92
    stufe
    0.92
     majeur
    0.90
     leçon
    0.90
     bridesmaids
    0.90
    教え
    0.88
     légère
    0.86
    Activations Density 0.026%

    No Known Activations