© 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. 9520
    Prev
    Next
    INDEX
    Explanations

    I am, is, am

    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
    鹩
    -1.17
     dicono
    -1.05
    笮
    -1.02
    ḫ
    -1.00
     kwar
    -0.99
    annten
    -0.98
    axaca
    -0.97
     Produits
    -0.95
    ètement
    -0.94
    ETHING
    -0.94
    POSITIVE LOGITS
     and
    1.24
     */
    1.07
     */
    0.98
     👎
    0.88
     how
    0.87
     early
    0.86
     July
    0.84
    텅
    0.84
     December
    0.84
     frühen
    0.84
    Activations Density 0.039%

    No Known Activations