© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 19894
    Prev
    Next
    INDEX
    Explanations

    action verbs or plan

    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_31_width_65k_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
    🤥
    0.64
     याचे
    0.61
    {
    0.59
    د
    0.59
     obce
    0.58
     sexes
    0.56
    ximity
    0.56
    👽
    0.55
           
    0.55
    TR
    0.55
    POSITIVE LOGITS
     action
    1.24
     Action
    1.13
    Action
    1.08
    action
    1.02
     ACTION
    1.01
     acción
    1.00
    アクション
    0.98
    动作
    0.96
    getAction
    0.94
     действие
    0.91
    Activations Density 0.054%

    No Known Activations