© 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. 22-GEMMASCOPE-RES-131K
    4. 93138
    Prev
    Next
    INDEX
    Explanations

    prepositions and topics discussed

    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
     ARISING
    -1.42
    뿡
    -1.38
    茑
    -1.37
     teléfono
    -1.35
     vertrouwen
    -1.34
    ໊
    -1.34
    vertissement
    -1.34
    gencias
    -1.33
     Ofrece
    -1.33
     configurações
    -1.30
    POSITIVE LOGITS
     and
    1.39
     issues
    1.38
     both
    1.37
     of
    1.30
     topics
    1.23
     related
    1.18
     various
    1.17
     approaches
    1.16
    both
    1.14
    توضیحات
    1.11
    Activations Density 0.073%

    No Known Activations