© 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. 34-GEMMASCOPE-RES-131K
    4. 33378
    Prev
    Next
    INDEX
    Explanations

    pre- and post- event contexts

    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_34/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
    operatively
    -0.92
     nowych
    -0.92
    coffret
    -0.89
     nové
    -0.85
    miques
    -0.84
    かわいい
    -0.84
     defStyle
    -0.83
    puerta
    -0.83
     quiso
    -0.83
     initWithFrame
    -0.83
    POSITIVE LOGITS
     vous
    0.84
     its
    0.82
     because
    0.78
     and
    0.78
    </h1>
    0.75
    ísima
    0.73
     There
    0.73
    ROG
    0.72
    部の
    0.71
     Spiele
    0.71
    Activations Density 0.085%

    No Known Activations