© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43093
    Prev
    Next
    INDEX
    Explanations

    making choices and purchases

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

    property regulations and availability

    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
     शीजान
    0.49
    रोग
    0.45
     remplacer
    0.45
     มัน
    0.44
     วิธี
    0.43
     నాలుగు
    0.43
    替换
    0.42
    㚅
    0.42
     componentes
    0.41
    函數
    0.41
    POSITIVE LOGITS
     immovable
    0.50
    deadline
    0.41
    ৃহ
    0.40
     notions
    0.39
     inflex
    0.39
     inflexible
    0.38
    inset
    0.37
     sportswear
    0.37
    Deadline
    0.37
     sprung
    0.36
    Activations Density 0.007%

    No Known Activations