© 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. 65127
    Prev
    Next
    INDEX
    Explanations

    ice and its states

    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
    ant
    -1.72
    ong
    -1.70
    7
    -1.69
    .
    -1.63
    9
    -1.55
    er
    -1.51
    return
    -1.50
     ۱۳
    -1.45
    rozco
    -1.45
    atives
    -1.43
    POSITIVE LOGITS
     sentada
    1.73
     representado
    1.65
     marcada
    1.62
    伃
    1.62
    麁
    1.55
     circunstan
    1.51
     Según
    1.48
     rallied
    1.46
     firmado
    1.45
     prized
    1.45
    Activations Density 0.031%

    No Known Activations