© 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. 22-GEMMASCOPE-RES-131K
    7. 79778
    Prev
    Next
    INDEX
    Explanations

    key-value definitions

    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_22/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
    صلاح
    -0.95
    perfil
    -0.93
     Allgemeinen
    -0.89
     Ră
    -0.89
     what
    -0.88
    azawa
    -0.85
    cendo
    -0.85
    haden
    -0.84
     escritora
    -0.83
    Frankreich
    -0.82
    POSITIVE LOGITS
    </b>
    1.20
    銑
    1.05
    RO
    0.97
     chacun
    0.96
    acate
    0.92
    </i>
    0.90
    TIA
    0.90
    𝒊
    0.89
    ELF
    0.88
    지만
    0.88
    Activations Density 0.001%

    No Known Activations