© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77877
    Prev
    Next
    INDEX
    Explanations

    article followed by noun

    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
     belangrijkste
    -1.19
     newest
    -1.17
    匆
    -1.13
     إحدى
    -1.09
     membuka
    -1.07
     gleichen
    -1.03
    ंप
    -1.02
    気持ちが
    -1.02
     principais
    -1.02
     merupakan
    -1.02
    POSITIVE LOGITS
    (!__
    1.39
     certain
    1.37
     considerable
    1.24
     of
    1.19
     cierta
    1.15
     few
    1.13
    что
    1.10
     determinado
    1.10
     fairly
    1.05
     such
    1.05
    Activations Density 0.009%

    No Known Activations