© 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. 22-GEMMASCOPE-RES-131K
    7. 130978
    Prev
    Next
    INDEX
    Explanations

    image shake correction, stability, variability

    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
    odoo
    -0.96
    lassification
    -0.93
    Inverse
    -0.90
     vettore
    -0.88
    solr
    -0.87
    ABU
    -0.87
     âm
    -0.86
    ellees
    -0.86
     costumi
    -0.85
    utoff
    -0.84
    POSITIVE LOGITS
     stabilize
    1.06
     stabilité
    1.02
     Stability
    1.02
     stability
    1.02
     stea
    0.99
     instability
    0.98
    Stability
    0.98
    稳定
    0.98
     ruhig
    0.97
     stabili
    0.96
    Activations Density 0.099%

    No Known Activations