© 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. 7752
    Prev
    Next
    INDEX
    Explanations

    renewal reference semi jobs practical

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

    multilingual programming tokens

    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
     this
    0.28
     upregulated
    0.28
     {
    0.27
     phosphorylated
    0.26
     https
    0.26
     genomics
    0.25
     messaging
    0.25
     Myanmar
    0.25
     perfused
    0.25
     dashed
    0.25
    POSITIVE LOGITS
    ד
    0.34
    utiliser
    0.33
    esprit
    0.32
     ד
    0.31
    르
    0.31
    kosten
    0.31
    ת
    0.31
    proble
    0.30
    Telefon
    0.30
    מו
    0.30
    Activations Density 1.730%

    No Known Activations