© 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. 22-GEMMASCOPE-RES-131K
    7. 40240
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
     and
    -1.24
     this
    -1.16
    N
    -1.14
     gedeelte
    -1.12
     surpresa
    -1.10
    L
    -1.08
    ">
    -1.05
     onderhoud
    -1.04
    wählen
    -1.02
     stedet
    -1.02
    POSITIVE LOGITS
    を
    1.42
    もしか
    1.41
     in
    1.30
     причем
    1.30
    曲は
    1.28
    參考文獻
    1.25
     rigide
    1.13
    特長
    1.12
    個人的には
    1.09
    醍
    1.09
    Activations Density 0.226%

    No Known Activations