© 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. 104003
    Prev
    Next
    INDEX
    Explanations

    materials like wood, pearl, amber

    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
     moze
    -1.20
    hoka
    -1.19
     paraíso
    -1.17
     zwi
    -1.16
     Maturity
    -1.15
     ayaa
    -1.13
     landen
    -1.09
    ientras
    -1.09
    LLVM
    -1.08
     представлены
    -1.08
    POSITIVE LOGITS
     them
    1.30
     this
    1.13
    ?}
    1.11
     понадоби
    1.10
     уже
    1.10
     proactive
    1.10
     pequeñas
    1.09
    赅
    1.09
    公立
    1.09
    ‑
    1.07
    Activations Density 0.044%

    No Known Activations