© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9786
    Prev
    Next
    INDEX
    Explanations

    structuring or linking concepts

    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
    jš
    0.34
    setAutoDraw
    0.33
     vidéos
    0.32
    सूर्य
    0.32
     נוס
    0.32
    㞖
    0.32
     भूकंप
    0.32
    ⴹ
    0.32
    निर
    0.31
     besuchen
    0.31
    POSITIVE LOGITS
     alkalinity
    0.33
     establishing
    0.32
     structuring
    0.32
     diagnosed
    0.31
     establishes
    0.30
     diagnosis
    0.30
     Branding
    0.30
     molecular
    0.30
     sizing
    0.30
     protective
    0.29
    Activations Density 0.246%

    No Known Activations