© 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. 22-GEMMASCOPE-RES-131K
    4. 13283
    Prev
    Next
    INDEX
    Explanations

    tipping point, back seat, take focus

    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_22/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
     which
    -1.23
    𝒙
    -0.96
     большое
    -0.96
    Mhm
    -0.93
    ությ
    -0.93
     gesammelt
    -0.92
    ख
    -0.91
     étudiants
    -0.89
     and
    -0.89
     réalisées
    -0.87
    POSITIVE LOGITS
     here
    1.24
     segü
    1.13
     treball
    1.05
     freio
    1.05
    ību
    1.03
     revelou
    1.03
    陕西
    1.03
     anunciou
    1.03
     потому
    1.02
     respondeu
    1.02
    Activations Density 0.038%

    No Known Activations