© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68332
    Prev
    Next
    INDEX
    Explanations

    intuitive and instinctual

    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
    actéristi
    -2.44
    鴴
    -2.42
    雱
    -2.23
    ágenes
    -2.20
    лся
    -2.20
    ritsar
    -2.11
    黩
    -2.03
     freaking
    -1.98
    뚠
    -1.96
    䛗
    -1.92
    POSITIVE LOGITS
    .
    2.44
     allow
    2.00
     prevents
    1.91
     but
    1.88
     thinks
    1.80
    AutoresizingMask
    1.79
    ↵↵
    1.77
     servings
    1.63
    béco
    1.63
     protect
    1.63
    Activations Density 0.017%

    No Known Activations