© 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. 55818
    Prev
    Next
    INDEX
    Explanations

    reminds us, sure looks, we know

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

    Academic topics, specific places, fabric

    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
     справи
    0.54
     لإ
    0.46
     সেটা
    0.46
     распоря
    0.44
     &
    0.42
    стви
    0.42
     ব্যবস্থাপনা
    0.42
     CBI
    0.42
     sprung
    0.42
    ,[
    0.42
    POSITIVE LOGITS
    떤
    0.44
     Almanya
    0.43
     isEqual
    0.43
    undur
    0.43
    وری
    0.42
     totam
    0.42
     utilizan
    0.41
     thèse
    0.41
    ammable
    0.41
     Allemagne
    0.41
    Activations Density 0.000%

    No Known Activations