© 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. 96388
    Prev
    Next
    INDEX
    Explanations

    business revenue and sales

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

    negative or problematic concepts

    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
    ↵
    0.59
     preposition
    0.46
     disputed
    0.44
     select
    0.44
     marm
    0.44
     beta
    0.44
     photo
    0.43
    ក្នុង
    0.43
     NDVI
    0.43
     Marm
    0.42
    POSITIVE LOGITS
    Ḩ
    0.50
     étudiants
    0.48
     dédi
    0.47
    Qaeda
    0.46
     dédiée
    0.45
    blico
    0.45
     bottlene
    0.45
     เด็ก
    0.44
    Chiều
    0.44
    Ⲇ
    0.44
    Activations Density 0.001%

    No Known Activations