© 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. 13111
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     their
    -1.16
     étudi
    -1.12
     timmar
    -1.09
    ležité
    -1.05
     DENSITY
    -1.04
    əl
    -1.04
    🏗
    -1.04
     occafion
    -1.01
    ölkerung
    -1.00
    臺北
    -0.98
    POSITIVE LOGITS
    |_{\
    1.18
     TAMBÉM
    1.16
     Wednesday
    1.16
     pertumbuhan
    1.13
     Tuesday
    1.08
     centimetres
    1.06
    ophyllum
    1.03
     dilaksanakan
    1.03
    shadowColor
    1.02
    indrome
    1.01
    Activations Density 0.014%

    No Known Activations