© 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. 10-GEMMASCOPE-RES-131K
    4. 981
    Prev
    Next
    INDEX
    Explanations

    stepping down or leaving positions

    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
     Dokter
    -1.79
     Dingen
    -1.70
     Empieza
    -1.63
     Deel
    -1.63
     Aprove
    -1.62
     underlines
    -1.62
     Quien
    -1.59
     Permite
    -1.59
     Falta
    -1.58
    𖥻
    -1.57
    POSITIVE LOGITS
     in
    2.02
     as
    1.64
     after
    1.48
    on
    1.48
     including
    1.46
    ↵
    1.43
    R
    1.38
    D
    1.37
    ’
    1.36
    So
    1.35
    Activations Density 0.013%

    No Known Activations