© 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. 22-GEMMASCOPE-RES-131K
    4. 12661
    Prev
    Next
    INDEX
    Explanations

    prefixes to proper nouns or brands

    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_22/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
     favoris
    -1.38
    푠
    -1.30
     utilizzati
    -1.27
     poliuret
    -1.19
    italien
    -1.19
     asfalto
    -1.18
    ----------
    
    -1.16
     bobina
    -1.14
     portugu
    -1.11
    ẏ
    -1.11
    POSITIVE LOGITS
    f
    1.26
    r
    1.23
    n
    1.20
    b
    1.13
    can
    1.13
    one
    1.12
    no
    1.11
    M
    1.09
    tr
    1.08
    éez
    1.07
    Activations Density 0.068%

    No Known Activations