© 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. 34-GEMMASCOPE-RES-131K
    7. 11919
    Prev
    Next
    INDEX
    Explanations

    the specific language

    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_34/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
    ╧
    -0.81
     շ
    -0.80
     pauvre
    -0.76
     Diagrams
    -0.75
     Cleansing
    -0.75
    腾讯
    -0.74
     قاعده
    -0.74
    wiąz
    -0.73
     now
    -0.73
    Activation
    -0.72
    POSITIVE LOGITS
     specific
    0.92
    kowy
    0.81
    бурге
    0.77
    كذا
    0.77
    (\"
    0.77
     upstream
    0.76
    itä
    0.73
    language
    0.73
    riebene
    0.73
    pecific
    0.73
    Activations Density 0.110%

    No Known Activations