© 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. 10-GEMMASCOPE-RES-131K
    4. 48149
    Prev
    Next
    INDEX
    Explanations

    one and victory

    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_10/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
     食堂
    -1.45
    Indians
    -1.33
    Ethio
    -1.32
    Azur
    -1.26
     cipher
    -1.24
    Gothic
    -1.20
     chimie
    -1.20
    Finance
    -1.19
    Rhin
    -1.19
    Parc
    -1.17
    POSITIVE LOGITS
     same
    1.94
    by
    1.42
    through
    1.37
    same
    1.37
     necessária
    1.34
    >{@
    1.30
     necessário
    1.30
     each
    1.30
     latter
    1.29
    like
    1.28
    Activations Density 0.041%

    No Known Activations