© 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. 42015
    Prev
    Next
    INDEX
    Explanations

    design and development

    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
     ARISING
    -1.36
     they
    -1.27
    imbawa
    -1.24
    ISTICS
    -1.23
    Shouldn
    -1.23
    need
    -1.21
    they
    -1.21
     такая
    -1.20
    set
    -1.19
     verfügb
    -1.17
    POSITIVE LOGITS
     for
    1.58
     and
    1.51
     ftate
    1.30
    เพื่อ
    1.28
    。"
    1.26
     betekenis
    1.24
     if
    1.23
    Ça
    1.23
     növény
    1.23
     criança
    1.21
    Activations Density 0.032%

    No Known Activations