© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 29443
    Prev
    Next
    INDEX
    Explanations

    cloud services and technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cloud
    1.05
     clouds
    1.02
    雲
    0.98
    cloud
    0.94
     Clouds
    0.88
    clouds
    0.86
    Cloud
    0.85
    云
    0.85
     Cloud
    0.84
    クラウド
    0.83
    POSITIVE LOGITS
     mussels
    0.43
     اش
    0.40
     関数
    0.40
     함수의
    0.40
     Bead
    0.38
    Px
    0.38
     kredi
    0.38
    owe
    0.38
     Ash
    0.38
     מה
    0.38
    Activations Density 0.003%

    No Known Activations