© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47928
    Prev
    Next
    INDEX
    Explanations

    field theories and shooters

    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_10/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
    1
    -1.41
    2
    -1.27
    4
    -1.24
     มือ
    -1.23
    ウム
    -1.20
    3
    -1.19
     สำ
    -1.18
    üse
    -1.16
     Comments
    -1.15
     Concerning
    -1.15
    POSITIVE LOGITS
     Exactos
    1.24
     it
    1.23
     |]
    1.20
     merusak
    1.19
    standigheden
    1.17
     íntimo
    1.17
     menolak
    1.16
     tujuan
    1.14
     there
    1.13
     anyone
    1.13
    Activations Density 0.055%

    No Known Activations