© 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. 54003
    Prev
    Next
    INDEX
    Explanations

    spelling bee, warning signs, submarine rendering, parliamentary briefing

    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
    螓
    -1.16
    initState
    -1.03
     kimi
    -1.02
    userInfo
    -1.01
    比较好
    -1.00
    Secara
    -0.99
     öf
    -0.96
    haped
    -0.94
     naturen
    -0.94
    bered
    -0.94
    POSITIVE LOGITS
     shown
    1.46
     at
    1.34
     showing
    1.30
     from
    1.27
     during
    1.23
     pictured
    1.16
     image
    1.14
     July
    1.13
     even
    1.08
     seen
    1.05
    Activations Density 0.221%

    No Known Activations