© 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. 104263
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be' followed by descriptor

    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
     Pradesh
    -1.29
    il
    -1.29
    --;
    -1.28
    illi
    -1.26
    ške
    -1.24
    },
    -1.23
    垕
    -1.21
     forKey
    -1.20
     or
    -1.19
    什么事
    -1.18
    POSITIVE LOGITS
     but
    1.40
    既に
    1.27
    :”
    1.25
    ,
    1.21
    燗
    1.16
     jovens
    1.11
    を選
    1.10
    すでに
    1.09
    нятие
    1.09
     anún
    1.07
    Activations Density 0.031%

    No Known Activations