© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 700
    Prev
    Next
    INDEX
    Explanations

    for purpose

    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
     nombreuses
    -1.50
     kalender
    -1.36
    anmoins
    -1.34
    ことができました
    -1.34
    '/>
    -1.30
     сад
    -1.30
     gustar
    -1.27
     Bakter
    -1.26
    蛳
    -1.25
    Quais
    -1.24
    POSITIVE LOGITS
     their
    1.45
     nothing
    1.32
     Interested
    1.31
     not
    1.30
    <em>
    1.28
     être
    1.27
    娄
    1.27
     no
    1.23
     also
    1.23
     only
    1.22
    Activations Density 0.034%

    No Known Activations