© 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. 7052
    Prev
    Next
    INDEX
    Explanations

    words that start phrases

    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
    lichem
    -1.26
    dö
    -1.19
     nadru
    -1.14
    isine
    -1.07
    给我
    -1.06
     sencillas
    -1.05
    ensaft
    -1.05
    අ
    -1.05
     habitantes
    -1.05
     kí
    -1.04
    POSITIVE LOGITS
     to
    1.30
    。
    1.20
     have
    1.16
     of
    1.16
     Inglés
    1.10
     bởi
    1.02
     aikana
    1.02
     been
    1.02
     muß
    1.02
    のための
    1.01
    Activations Density 0.004%

    No Known Activations