© 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. 9140
    Prev
    Next
    INDEX
    Explanations

    pipe, cigar, pan, go

    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
     muita
    -1.39
    寝る
    -1.38
     dobré
    -1.33
    两者
    -1.32
    風景
    -1.30
     verksamhet
    -1.27
    Comida
    -1.25
    自由に
    -1.23
     arbete
    -1.22
    ämpfer
    -1.21
    POSITIVE LOGITS
    辱
    1.39
    ();
    1.32
    neval
    1.30
     About
    1.27
     de
    1.27
     tentang
    1.26
            
    1.23
    衛隊
    1.23
     wegen
    1.20
    })$.
    1.20
    Activations Density 0.009%

    No Known Activations