© 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. 34-GEMMASCOPE-RES-131K
    7. 23805
    Prev
    Next
    INDEX
    Explanations

    multilingual technical discussions

    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_34/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
    InjectMocks
    -1.36
     ďal
    -1.31
    کیف
    -1.25
     memanfaatkan
    -1.20
     tých
    -1.19
    וּ
    -1.16
     понадобится
    -1.14
     všetkých
    -1.13
    chenta
    -1.13
     потребуется
    -1.12
    POSITIVE LOGITS
     which
    1.30
     whilst
    1.27
    liath
    1.22
    非常的
    1.18
     πρ
    1.15
     katika
    1.14
    の為
    1.13
    gradable
    1.13
    (||
    1.13
    ToMany
    1.13
    Activations Density 0.046%

    No Known Activations