© 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. 19878
    Prev
    Next
    INDEX
    Explanations

    never fails to lift

    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
    ↵↵
    -1.33
    s
    -1.17
    1
    -1.10
    <h2>
    -1.09
    ........
    -1.04
     not
    -1.03
    S
    -1.03
    ↵↵↵↵
    -1.02
    ....
    -1.02
     ومن
    -1.02
    POSITIVE LOGITS
     хорошая
    1.32
    ⸨
    1.29
    himo
    1.29
    𝑿
    1.27
     Pued
    1.26
     Aún
    1.25
     impecable
    1.24
    这事
    1.23
    painel
    1.23
     możliwość
    1.23
    Activations Density 0.033%

    No Known Activations