© 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. 22-GEMMASCOPE-RES-131K
    7. 70866
    Prev
    Next
    INDEX
    Explanations

    of [attribute noun or adjective]

    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
    着自己的
    -1.28
     the
    -1.23
    vät
    -1.20
    瞟
    -1.09
     prawda
    -1.09
    anians
    -1.08
    :
    -1.07
    接続
    -1.07
    杀手
    -1.05
     emplois
    -1.05
    POSITIVE LOGITS
    まず
    1.27
     only
    1.27
     також
    1.24
     despertar
    1.20
     también
    1.20
     вони
    1.20
     not
    1.19
     também
    1.18
     fewer
    1.17
     mostly
    1.16
    Activations Density 0.044%

    No Known Activations