© 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. 10-GEMMASCOPE-RES-131K
    7. 127412
    Prev
    Next
    INDEX
    Explanations

    specific behaviors

    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_10/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
    橚
    -3.36
    戬
    -2.25
    怍
    -2.23
    觏
    -2.20
    ⟞
    -2.20
    ྃ
    -2.17
    it
    -2.06
    鲽
    -2.05
    ～！
    -2.02
    a
    -2.02
    POSITIVE LOGITS
     behaviours
    2.30
     behaviors
    2.27
    _
    2.05
    フラワー
    1.95
    問合せ
    1.88
    釹
    1.86
    -
    1.82
    
    1.77
     that
    1.76
    銫
    1.76
    Activations Density 0.005%

    No Known Activations