© 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. 84382
    Prev
    Next
    INDEX
    Explanations

    roots of words

    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
     acestea
    -1.17
    ocrine
    -1.13
    殮
    -1.06
    tainty
    -1.05
    irled
    -1.05
     Dinas
    -1.03
     Oblast
    -1.02
    orses
    -1.01
    tiously
    -1.00
     KCl
    -1.00
    POSITIVE LOGITS
     cristianismo
    1.09
     instituto
    1.01
     Obviously
    0.96
     แดง
    0.93
     Sábado
    0.93
     When
    0.92
     Mesmo
    0.91
     allerdings
    0.91
     sudah
    0.91
     After
    0.90
    Activations Density 0.084%

    No Known Activations