© 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. 70156
    Prev
    Next
    INDEX
    Explanations

    under specific circumstances

    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
    的东西
    -0.79
    込ま
    -0.77
     ogre
    -0.74
    |[]
    -0.73
     phe
    -0.71
    ⣾
    -0.71
    Complaints
    -0.71
    things
    -0.67
    轮胎
    -0.67
    同一个
    -0.67
    POSITIVE LOGITS
     circumstances
    5.31
    circum
    3.52
     circumstance
    3.47
     circunstancias
    3.38
     Circumstances
    3.30
    Circum
    2.98
     circonstances
    2.77
     обстоятельства
    2.67
     circum
    2.36
     circun
    2.36
    Activations Density 0.033%

    No Known Activations