© 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. 105923
    Prev
    Next
    INDEX
    Explanations

    vehicle steering and control

    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
     use
    -1.38
     biçim
    -1.19
    In
    -1.18
    但这
    -1.18
     yavaş
    -1.16
    use
    -1.14
     it
    -1.13
     —
    -1.11
    rrer
    -1.11
    elung
    -1.10
    POSITIVE LOGITS
     arkite
    1.20
    放到
    1.19
    إنه
    1.15
    ႐
    1.12
    angkutan
    1.12
    SAA
    1.12
    特有
    1.10
    ︲
    1.10
     tredje
    1.09
     Fazit
    1.09
    Activations Density 0.059%

    No Known Activations