© 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. 34-GEMMASCOPE-RES-131K
    7. 93698
    Prev
    Next
    INDEX
    Explanations

    BOOST CHECK

    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_34/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
    するもの
    -0.93
     undoubtedly
    -0.90
     more
    -0.89
     surprisingly
    -0.85
    瞿
    -0.84
     sost
    -0.79
    家は
    -0.79
     Surprisingly
    -0.77
    باح
    -0.77
    八月
    -0.77
    POSITIVE LOGITS
     forward
    0.91
    eb
    0.90
     Mum
    0.89
    og
    0.85
    ort
    0.85
     acclaimed
    0.85
     lmao
    0.84
    bf
    0.84
    丁寧に
    0.83
    Jeden
    0.83
    Activations Density 0.004%

    No Known Activations