© 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. 105935
    Prev
    Next
    INDEX
    Explanations

    Q: and PRECEDENTIAL

    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
     entsprechend
    -1.45
     What
    -1.36
     Перейти
    -1.34
    を感じ
    -1.32
     Which
    -1.32
     все
    -1.30
    FormUrlEncoded
    -1.30
     sprawling
    -1.29
     Required
    -1.27
    桄
    -1.27
    POSITIVE LOGITS
    on
    1.38
    itsubishi
    1.24
     ation
    1.23
    gambarkan
    1.23
    炻
    1.22
     entrées
    1.21
    licious
    1.20
     nivå
    1.19
    oczes
    1.16
     hdi
    1.15
    Activations Density 0.000%

    No Known Activations