© 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. 10-GEMMASCOPE-RES-131K
    7. 119442
    Prev
    Next
    INDEX
    Explanations

    interview, statement, blog post

    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
     used
    -1.30
    folgt
    -1.29
    WaitGroup
    -1.22
    ਾਈ
    -1.20
     utilizada
    -1.17
    vidla
    -1.16
     でき
    -1.13
     사용
    -1.13
    scl
    -1.12
     Нов
    -1.10
    POSITIVE LOGITS
     their
    1.33
    ⌜
    1.30
     than
    1.27
    بور
    1.26
    antism
    1.25
    ↱
    1.24
    idopsis
    1.20
    」(
    1.20
    didReceive
    1.20
     jedoch
    1.19
    Activations Density 0.046%

    No Known Activations