© 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. 35948
    Prev
    Next
    INDEX
    Explanations

    child, promo, Echo, Node, A, Pass, client

    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
    unfortunately
    -1.25
    whatever
    -1.16
     ferocious
    -1.14
    fillType
    -1.11
    
    -1.11
    took
    -1.10
     consac
    -1.07
     aplik
    -1.07
     SIX
    -1.06
     ridiculously
    -1.06
    POSITIVE LOGITS
     establish
    1.16
     establishing
    1.10
     actually
    1.05
    hadapi
    0.96
     create
    0.96
     getting
    0.94
    towany
    0.94
    哔
    0.93
    هور
    0.91
     exquisitely
    0.91
    Activations Density 0.001%

    No Known Activations