© 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. 12647
    Prev
    Next
    INDEX
    Explanations

    datasheet, datasource

    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
    狲
    -2.59
    VERTISEMENT
    -2.44
    bilden
    -2.38
    carbons
    -2.36
    崃
    -2.33
    outWeight
    -2.28
    鲧
    -2.28
    ৄ
    -2.27
    εται
    -2.27
     tuan
    -2.25
    POSITIVE LOGITS
    ar
    3.09
    re
    2.98
    彼が
    2.91
    4
    2.81
    A
    2.72
    for
    2.70
    {
    2.55
    C
    2.55
    S
    2.55
    ...
    2.55
    Activations Density 0.001%

    No Known Activations