© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67896
    Prev
    Next
    INDEX
    Explanations

    years and deaths

    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
     inaugura
    -1.34
     papir
    -1.24
     lupa
    -1.19
     hunde
    -1.16
     magist
    -1.14
    ↖
    -1.14
     lilla
    -1.12
     Parfum
    -1.09
    vaného
    -1.08
     istan
    -1.06
    POSITIVE LOGITS
     verdaderas
    1.13
     maravillosas
    1.12
    釐
    1.09
    <eos>
    1.08
     and
    1.03
     lluvias
    1.02
     encima
    1.00
     vivere
    0.96
    いっ
    0.96
     hecha
    0.96
    Activations Density 0.001%

    No Known Activations