© 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. 134238
    Prev
    Next
    INDEX
    Explanations

    still remains, API URL, name follows

    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
    TASK
    0.35
    负
    0.35
    enbach
    0.35
     прием
    0.34
    탑
    0.34
     ")"
    0.34
    jø
    0.34
    agangan
    0.33
    unsch
    0.33
    ünsche
    0.33
    POSITIVE LOGITS
     independently
    0.41
     الداخلية
    0.40
    ፈ
    0.39
    มิ
    0.38
     المق
    0.37
     ऑर
    0.37
     Et
    0.36
     zetten
    0.36
     hoàn
    0.36
    たま
    0.36
    Activations Density 0.001%

    No Known Activations