© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 627
    Prev
    Next
    INDEX
    Explanations

    team performance and outcomes

    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
    Kdo
    -1.28
    Podob
    -1.27
    Selain
    -1.27
    </h2>
    -1.26
     tästä
    -1.24
    Menurutnya
    -1.23
    Namun
    -1.23
    浒
    -1.23
    同上
    -1.23
    These
    -1.22
    POSITIVE LOGITS
     in
    1.81
     I
    1.31
     The
    1.25
    𝑢
    1.21
    ukunfts
    1.20
     on
    1.18
    SOS
    1.16
     umbrella
    1.15
    cabo
    1.15
     under
    1.12
    Activations Density 0.089%

    No Known Activations