© 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. 98388
    Prev
    Next
    INDEX
    Explanations

    time followed by action

    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
     princí
    -1.23
     an
    -1.21
     afirmó
    -1.20
    subfigure
    -1.20
     establecido
    -1.17
     stí
    -1.15
     any
    -1.12
     no
    -1.12
     introducido
    -1.12
     zobac
    -1.10
    POSITIVE LOGITS
     citroen
    1.45
     conster
    1.42
     latine
    1.40
     assister
    1.39
     vanille
    1.38
     prostitu
    1.33
     reputa
    1.32
    躥
    1.30
     rester
    1.30
     toilette
    1.30
    Activations Density 0.094%

    No Known Activations