© 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. 34-GEMMASCOPE-RES-131K
    7. 54239
    Prev
    Next
    INDEX
    Explanations

    minimally invasive

    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
    gewiesen
    -1.10
    ㈩
    -1.02
     Relaciones
    -0.97
     Atención
    -0.92
     Selecciona
    -0.92
     Communists
    -0.92
     Tiene
    -0.91
     totalité
    -0.91
    Daniele
    -0.91
     Artículo
    -0.90
    POSITIVE LOGITS
    istic
    1.43
     but
    1.37
     amount
    1.31
     Minimal
    1.31
     effort
    1.28
     minim
    1.27
     viable
    1.24
     disruption
    1.21
     minimal
    1.20
     invasive
    1.16
    Activations Density 0.017%

    No Known Activations