© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40480
    Prev
    Next
    INDEX
    Explanations

    Hardware and infrastructure components

    np_acts-logits-general · gemini-2.5-flash-lite

    technical infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᱔
    0.38
     ለ
    0.36
    成果
    0.36
    用途
    0.36
    顷
    0.36
    rocery
    0.34
     rootView
    0.34
     барои
    0.34
    ᱗
    0.34
    掳
    0.34
    POSITIVE LOGITS
     Hardware
    0.35
     Infrast
    0.34
     infrastrukt
    0.34
    Hardware
    0.34
     procedural
    0.33
     infrast
    0.33
    hardware
    0.33
    Personnel
    0.33
    Infrastructure
    0.33
    Platform
    0.32
    Activations Density 0.197%

    No Known Activations