© 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. 32872
    Prev
    Next
    INDEX
    Explanations

    most + frequency/likelihood

    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
     more
    -1.52
     più
    -1.39
     bardziej
    -1.20
     более
    -1.19
     hơn
    -1.13
     більш
    -1.13
    更
    -1.09
     bardzo
    -1.04
     daugiau
    -1.02
    更加
    -1.01
    POSITIVE LOGITS
     likely
    2.59
     often
    2.39
    Often
    1.84
     часто
    1.70
    likely
    1.68
     commonly
    1.62
     Often
    1.60
    often
    1.56
     frequently
    1.53
     Likely
    1.53
    Activations Density 0.059%

    No Known Activations