© 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. 10-GEMMASCOPE-RES-131K
    7. 101546
    Prev
    Next
    INDEX
    Explanations

    raid and raiding expeditions

    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
     this
    -1.59
    <strong>
    -1.55
     apartamentos
    -1.50
     amargo
    -1.48
    before
    -1.45
     uñas
    -1.43
    ogeneous
    -1.42
     decoraciones
    -1.38
    which
    -1.36
     plásticos
    -1.34
    POSITIVE LOGITS
     are
    1.56
    Zitat
    1.49
     ?.
    1.48
     sogar
    1.48
     Such
    1.41
     motto
    1.40
     WOULD
    1.38
     manifiesta
    1.38
    楽しむ
    1.37
    ˧
    1.37
    Activations Density 0.041%

    No Known Activations