© 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. 240390
    Prev
    Next
    INDEX
    Explanations

    improved economic conditions

    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
    CENT
    0.55
    AH
    0.50
     Carrick
    0.47
    ardia
    0.47
     න
    0.45
     hérit
    0.45
     bhavanti
    0.44
     arabe
    0.44
     Tá
    0.44
    Poly
    0.44
    POSITIVE LOGITS
    dust
    0.50
    訊
    0.47
    讯
    0.44
    verbosity
    0.44
    inery
    0.42
     ور
    0.42
                              
    0.41
    communications
    0.41
     রক্ষণ
    0.41
    तुर
    0.40
    Activations Density 0.001%

    No Known Activations