© 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. 84208
    Prev
    Next
    INDEX
    Explanations

    paper sizes like A4, A5

    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
     RISERVATA
    -0.75
     möchtest
    -0.71
    ONSORED
    -0.68
    Pontos
    -0.68
    depression
    -0.68
     willst
    -0.68
    avas
    -0.68
    ༠
    -0.67
    thia
    -0.67
     Commencement
    -0.66
    POSITIVE LOGITS
     A
    1.80
     paper
    1.48
     формат
    1.28
    paper
    1.25
     size
    1.23
    format
    1.21
     format
    1.20
     DIN
    1.19
    size
    1.18
     Letter
    1.13
    Activations Density 0.031%

    No Known Activations