© 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. 53978
    Prev
    Next
    INDEX
    Explanations

    foundation and building blocks

    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
    allclose
    -0.83
    hinter
    -0.82
    Daughter
    -0.78
    samt
    -0.77
    magazin
    -0.74
    ovala
    -0.74
    brainly
    -0.73
     --;
    -0.72
    kalender
    -0.72
    klart
    -0.71
    POSITIVE LOGITS
     foundation
    3.53
     foundations
    3.23
    foundation
    2.58
     building
    2.28
    Foundation
    2.08
     FOUNDATION
    2.06
     bricks
    2.05
     Foundations
    2.03
     Foundation
    1.99
     foundational
    1.96
    Activations Density 0.031%

    No Known Activations