© 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. 10-GEMMASCOPE-RES-131K
    7. 68212
    Prev
    Next
    INDEX
    Explanations

    cities, states, and countries

    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_10/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
     there
    -1.54
     alojamientos
    -1.49
     they
    -1.47
     aceites
    -1.42
     hogares
    -1.41
     jungen
    -1.40
    alarme
    -1.36
    !
    -1.31
     nhưng
    -1.30
     your
    -1.27
    POSITIVE LOGITS
     of
    1.30
     moks
    1.19
    rene
    1.15
    酝
    1.11
     variante
    1.05
    Географија
    1.05
    SUFFIX
    1.04
     pulsa
    1.04
     febr
    1.04
    itattu
    1.03
    Activations Density 0.219%

    No Known Activations