© 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. 22-GEMMASCOPE-RES-131K
    7. 68443
    Prev
    Next
    INDEX
    Explanations

    z, Z, C, third, axes

    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
    ާ
    -1.19
     твой
    -1.16
     BrowserModule
    -1.14
     ürün
    -1.10
    encore
    -1.08
    visuel
    -1.05
    ğum
    -1.05
     będ
    -1.05
     daewoo
    -1.05
    ndar
    -1.04
    POSITIVE LOGITS
     (
    1.20
     —
    1.10
     r
    1.10
     as
    1.08
     }
    1.07
    )
    1.07
     [
    1.05
    !
    1.05
     треть
    1.04
     t
    1.03
    Activations Density 0.035%

    No Known Activations