© 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. 206855
    Prev
    Next
    INDEX
    Explanations

    compliance SALE demand cut

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

    penis, tuberculosis tissue

    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
    ري
    0.55
    闔
    0.49
    好
    0.47
     رپور
    0.46
    
    0.45
    使用
    0.43
     ιδια
    0.43
    Მ
    0.42
    较大的
    0.42
    Ὑ
    0.42
    POSITIVE LOGITS
    t
    0.55
     prudence
    0.54
     Chern
    0.48
     unaccount
    0.48
     Transcript
    0.47
     prudent
    0.46
     succinctly
    0.45
     segreg
    0.44
     tuberculosis
    0.44
     Schell
    0.43
    Activations Density 0.001%

    No Known Activations