© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73752
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
     bains
    -1.04
     it
    -0.98
     Dato
    -0.91
     жу
    -0.89
     Lagu
    -0.88
     marta
    -0.85
     disposição
    -0.84
     zui
    -0.82
     trist
    -0.82
     artikkelen
    -0.82
    POSITIVE LOGITS
    sbericht
    1.16
     exigencias
    1.09
     OGSÅ
    1.08
    ('../
    1.08
     motoru
    1.07
     penyanyi
    1.05
    ৄ
    1.04
    artney
    1.02
    珦
    1.02
    lillah
    1.01
    Activations Density 0.020%

    No Known Activations