© 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. 34-GEMMASCOPE-RES-131K
    4. 102427
    Prev
    Next
    INDEX
    Explanations

    compared to others

    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
    什么呢
    -1.05
     according
    -1.01
     itself
    -0.95
     them
    -0.93
     bulunabilir
    -0.89
    ệp
    -0.88
    以外にも
    -0.88
    یکس
    -0.88
    ilstein
    -0.86
     everytime
    -0.86
    POSITIVE LOGITS
     we
    1.65
     you
    1.63
     that
    1.41
     like
    1.34
     I
    1.20
    attempts
    1.20
     similares
    1.16
     around
    1.13
     in
    1.13
     of
    1.09
    Activations Density 0.072%

    No Known Activations