© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89765
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    ilität
    -1.38
     besonderes
    -1.26
     欣赏
    -1.20
     necessarie
    -1.20
    diseño
    -1.16
    後悔
    -1.15
    ranet
    -1.14
     Gedanke
    -1.11
    ご了承ください
    -1.09
     Konsequ
    -1.09
    POSITIVE LOGITS
    1
    1.62
    th
    1.54
    ra
    1.25
    ese
    1.23
    ene
    1.22
    ita
    1.22
    h
    1.21
    as
    1.20
    le
    1.18
    the
    1.17
    Activations Density 0.076%

    No Known Activations