© 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. 68414
    Prev
    Next
    INDEX
    Explanations

    months in dates

    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
    を行います
    -1.39
     today
    -1.26
     hoje
    -1.24
    U
    -1.23
     heutige
    -1.19
    M
    -1.16
    Q
    -1.15
    D
    -1.13
     oggi
    -1.12
    N
    -1.10
    POSITIVE LOGITS
    sió
    1.14
    子は
    1.13
    宝物
    1.08
    子の
    1.07
    rogène
    1.05
     autorisation
    1.03
    when
    1.02
    почка
    1.02
     when
    1.01
    Spel
    1.01
    Activations Density 0.006%

    No Known Activations