© 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. 20322
    Prev
    Next
    INDEX
    Explanations

    "this site" or "this article"

    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
     our
    -1.84
     algunos
    -1.61
     their
    -1.30
     mantienen
    -1.26
     Obrigado
    -1.25
     всех
    -1.22
    就可以了
    -1.22
     bigger
    -1.22
     wirklich
    -1.20
     sommige
    -1.20
    POSITIVE LOGITS
    はこの
    1.39
    </h1>
    1.23
    ⏤
    1.21
    ">−
    1.19
    eſ
    1.14
    áneamente
    1.12
     not
    1.12
    ></
    1.09
     bushels
    1.09
    是由
    1.08
    Activations Density 0.003%

    No Known Activations