© 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. 71872
    Prev
    Next
    INDEX
    Explanations

    other followed by a noun

    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
    ární
    -1.08
    ℋ
    -1.05
    årige
    -1.04
    åringen
    -1.03
    рыя
    -1.02
    ecutable
    -1.01
    ולוג
    -1.01
    beitet
    -0.99
    unità
    -0.98
    âts
    -0.98
    POSITIVE LOGITS
     information
    1.30
     Information
    1.09
     info
    1.05
    也可以
    1.02
     altre
    0.99
     other
    0.97
    ISSUE
    0.97
     informa
    0.96
     עוד
    0.96
     oltre
    0.94
    Activations Density 0.028%

    No Known Activations