© 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. 22-GEMMASCOPE-RES-131K
    4. 68385
    Prev
    Next
    INDEX
    Explanations

    the or his noun

    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_22/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
     informace
    -1.46
     aplikace
    -1.32
     zowel
    -1.30
     zarówno
    -1.28
     vendredi
    -1.26
     zapato
    -1.22
    ashboard
    -1.21
     втором
    -1.20
     annoncé
    -1.18
     traducir
    -1.16
    POSITIVE LOGITS
     had
    1.34
     by
    1.27
    噱
    1.20
     young
    1.17
     was
    1.15
     dalam
    1.13
     other
    1.10
     group
    1.07
    囯
    1.05
     could
    1.02
    Activations Density 0.044%

    No Known Activations