© 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. 10-GEMMASCOPE-RES-131K
    7. 104822
    Prev
    Next
    INDEX
    Explanations

    abbreviations or parts of words

    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
    ,
    -2.86
    ↵
    -2.66
    .
    -2.44
    ,”
    -2.38
    橚
    -2.23
    他们
    -2.08
     And
    -2.05
     Are
    -2.03
    并没有
    -2.00
    它
    -2.00
    POSITIVE LOGITS
     advise
    2.42
    𖤍
    2.30
    蕷
    2.25
    蓥
    2.22
    section
    2.20
    𓆩
    2.16
     ajuta
    2.14
     huile
    2.13
     extracto
    2.13
    いる
    2.09
    Activations Density 0.105%

    No Known Activations