© 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. 54035
    Prev
    Next
    INDEX
    Explanations

    these or those followed by nouns

    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
     которых
    -0.86
     concealer
    -0.84
     которые
    -0.81
     Motto
    -0.80
     situations
    -0.78
     Precipitation
    -0.78
     paella
    -0.77
    APPED
    -0.77
    きの
    -0.76
     oiseaux
    -0.76
    POSITIVE LOGITS
     surroundings
    1.47
     two
    1.43
     stairs
    1.38
     festivities
    1.31
     coordinates
    1.31
     credentials
    1.27
     lyrics
    1.22
     initials
    1.17
     ruins
    1.17
     proceedings
    1.16
    Activations Density 0.069%

    No Known Activations