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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9434
    Prev
    Next
    INDEX
    Explanations

    sequences after abbreviations

    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
     these
    -1.27
    といふ
    -1.23
     gracioso
    -1.22
     solucionar
    -1.20
     if
    -1.16
     two
    -1.13
     τά
    -1.13
     at
    -1.11
     when
    -1.10
    先は
    -1.09
    POSITIVE LOGITS
     simplu
    1.27
     myself
    1.22
     aici
    1.16
     ziua
    1.16
     fapt
    1.16
    脔
    1.15
     she
    1.15
     totul
    1.13
     trei
    1.12
     aceea
    1.09
    Activations Density 0.145%

    No Known Activations