© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13975
    Prev
    Next
    INDEX
    Explanations

    file name or xml namespace

    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
     its
    -1.58
     by
    -1.55
     even
    -1.44
     their
    -1.38
     both
    -1.37
     only
    -1.30
     Материал
    -1.27
     keep
    -1.24
     for
    -1.23
     all
    -1.22
    POSITIVE LOGITS
     Dinas
    1.25
     zyn
    1.23
    なので
    1.20
     leo
    1.19
    g
    1.17
    which
    1.16
     パッド
    1.15
    也可以
    1.15
    なども
    1.15
    kapelle
    1.14
    Activations Density 0.009%

    No Known Activations